retro
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data which could contain malicious instructions.\n
- Ingestion points: The skill reads session logs from the local machine and various repository files including
package.json, CI workflows,CLAUDE.md,AGENTS.md, andCODING_STANDARDS.mdas specified inSKILL.md.\n - Boundary markers: There are no instructions for the agent to use delimiters or ignore potentially malicious instructions embedded within the logs or repository files.\n
- Capability inventory: The skill possesses capabilities to read local files and provide recommendations to the user for environment and steering file modifications.\n
- Sanitization: The instructions do not define any sanitization or validation processes for the data read from logs or configuration files.
Audit Metadata