GHSA-J659-8XH6-5PQ5
Vulnerability from github – Published: 2026-08-17 21:50 – Updated: 2026-08-17 21:50_estimate_batch_cost (atomic_agents/agent.py) looks up the per-model output price with PRICING.get(model, {}), returning 0.0 for any model not in the hardcoded pricing table. _check_batch_reservation then early-returns when the reservation is <= 0, skipping the batch reservation entirely. That reservation is the only defense against the documented fan-out race where every parallel helper/delegate reads the identical pre-batch on-disk cost total and each passes its individual check even though the collective spend overruns the configured cap.
Impact: an operator running any model not in the pricing table (self-hosted/Ollama/vLLM, a new provider SKU) with cost_guardrails + daily_cap_usd set believes the cap protects them, but a single parallel batch can blow past the cap. The parallel-helper model argument can also be steered to an unknown id. The sibling dream._estimate_dream_cost does this correctly (PRICING.get(model, _fallback_pricing())), which makes this a clear defect.
Affected: agent.py (_estimate_batch_cost / _check_batch_reservation), all versions through 1.0.0.
Fix: use PRICING.get(model, _costs._fallback_pricing())['output'] (mirror dream/calc_cost). Add a conformance test asserting an unknown-model batch reserves > 0 and that an over-cap unknown-model batch raises CostGuardrailBlocked.
{
"affected": [
{
"database_specific": {
"last_known_affected_version_range": "\u003c= 1.0.0"
},
"package": {
"ecosystem": "PyPI",
"name": "atomic-agents-stack"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "1.1.0"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [],
"database_specific": {
"cwe_ids": [
"CWE-770"
],
"github_reviewed": true,
"github_reviewed_at": "2026-08-17T21:50:01Z",
"nvd_published_at": null,
"severity": "HIGH"
},
"details": "`_estimate_batch_cost` (`atomic_agents/agent.py`) looks up the per-model output price with `PRICING.get(model, {})`, returning 0.0 for any model not in the hardcoded pricing table. `_check_batch_reservation` then early-returns when the reservation is \u003c= 0, skipping the batch reservation entirely. That reservation is the only defense against the documented fan-out race where every parallel helper/delegate reads the identical pre-batch on-disk cost total and each passes its individual check even though the collective spend overruns the configured cap.\n\n**Impact:** an operator running any model not in the pricing table (self-hosted/Ollama/vLLM, a new provider SKU) with `cost_guardrails` + `daily_cap_usd` set believes the cap protects them, but a single parallel batch can blow past the cap. The parallel-helper `model` argument can also be steered to an unknown id. The sibling `dream._estimate_dream_cost` does this correctly (`PRICING.get(model, _fallback_pricing())`), which makes this a clear defect.\n\n**Affected:** `agent.py` (`_estimate_batch_cost` / `_check_batch_reservation`), all versions through 1.0.0.\n\n**Fix:** use `PRICING.get(model, _costs._fallback_pricing())[\u0027output\u0027]` (mirror dream/calc_cost). Add a conformance test asserting an unknown-model batch reserves \u003e 0 and that an over-cap unknown-model batch raises `CostGuardrailBlocked`.",
"id": "GHSA-j659-8xh6-5pq5",
"modified": "2026-08-17T21:50:01Z",
"published": "2026-08-17T21:50:01Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/dep0we/atomic-agents-stack/security/advisories/GHSA-j659-8xh6-5pq5"
},
{
"type": "PACKAGE",
"url": "https://github.com/dep0we/atomic-agents-stack"
},
{
"type": "WEB",
"url": "https://github.com/dep0we/atomic-agents-stack/releases#release-v1.1.0"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N",
"type": "CVSS_V4"
}
],
"summary": "atomic-agents-stack: Parallel helper/delegate batch reserves $0 for models absent from the pricing table, bypassing the cost-cap fan-out guard"
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
How durations are calculated
Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.
Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.
Loading timeline…
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.