retro
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data sources which could be manipulated to influence agent behavior.
- Ingestion points: The skill reads session logs and repository configuration files (e.g.,
package.json, CI workflows) to identify improvements. - Boundary markers: There are no instructions provided to use delimiters or ignore embedded instructions within the logs or repository files.
- Capability inventory: The skill possesses file-reading capabilities and the ability to invoke other skills (specifically
writing-for-agents). It does not demonstrate network exfiltration or arbitrary command execution capabilities. - Sanitization: No content sanitization or validation steps are defined for the analyzed logs or files.
Audit Metadata