factory-watchdog
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources such as user-authored task history, pull request (PR) descriptions, and branch names.
- Ingestion points: The skill instructs the agent to read user-authored history and PR state to verify authorization and task status in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the processed history or PR data.
- Capability inventory: While no code scripts are provided, the instructions describe notification and monitoring capabilities performed by the agent.
- Sanitization: There are no explicit mentions of sanitizing or validating the input data before processing it as part of the decision-making logic.
- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any accompanying scripts or dependency files for analysis.
Audit Metadata