foam-runs

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for running local maintenance scripts (scripts/runs.py, scripts/ledger_check.py) for simulation ledger management and deterministic repair. These are project-specific administrative utilities.\n- [PROMPT_INJECTION]: The skill reads external solver logs and the markdown ledger, which creates an indirect prompt injection surface.\n
  • Ingestion points: Simulation logs (log.<solver>), Allrun.out, and the runs/ledger.md file.\n
  • Boundary markers: The skill does not define specific delimiters to separate untrusted log data from agent instructions.\n
  • Capability inventory: Includes process termination (stop_case), ledger writing (set_run_note), and execution of local maintenance scripts.\n
  • Sanitization: There is no mention of sanitizing or validating simulation log content before it is read by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 06:05 AM
Security Audit — agent-trust-hub — foam-runs