stac-troubleshooter
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill is designed to execute local Python scripts (
scripts/stac_doctor.pyandscripts/check_build_outputs.py) for project diagnostics. This is the primary function of the skill and is considered safe within the intended context. - PROMPT_INJECTION (LOW): Category 8: Indirect Prompt Injection. The skill ingests untrusted data from the 'Failing command and output' input which could be used to influence the agent's behavior through adversarial content in error logs. Evidence Chain: 1. Ingestion point: SKILL.md 'Required Inputs' section. 2. Boundary markers: Absent. 3. Capability inventory: Execution of local diagnostic scripts. 4. Sanitization: Absent.
Audit Metadata