triage
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of changed files from untrusted branches or pull requests. A malicious file could contain instructions designed to manipulate the agent's triage summary or behavior.\n
- Ingestion points: Step 2 in
SKILL.mduses theReadtool to ingest file content from the changes detected in step 1.\n - Boundary markers: No specific delimiters or "ignore" instructions are provided to separate file content from the agent's own task instructions.\n
- Capability inventory: The agent has access to
Bash(git commands),Read,Grep, andGlobtools.\n - Sanitization: No sanitization or validation of the ingested file content is performed prior to the agent processing it for categorization.
Audit Metadata