retro
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes coding session logs (SKILL.md), which constitutes an ingestion point for potentially untrusted data. \n
- Ingestion points: Session logs and repository primary sources (SKILL.md). \n
- Boundary markers: The instructions do not specify the use of delimiters or warnings when processing log content. \n
- Capability inventory: The skill is limited to presenting findings to the user (SKILL.md Step 4). \n
- Sanitization: No explicit sanitization or filtering of log content is described.\n- [SAFE]: The skill does not access credentials, perform network requests, or execute remote code. It includes configuration (
disable-model-invocation: true) that restricts its execution environment.
Audit Metadata