story-repo-scout
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from story cards, tickets, and repository files which could contain malicious instructions.
- Ingestion points: Story card text, ticket descriptions, and the content of files throughout the repository identified in steps 1, 3, and 6.
- Boundary markers: The skill instructions do not specify explicit delimiters or warnings to ignore embedded instructions in the untrusted input.
- Capability inventory: The skill uses file inspection and search tools (ripgrep); however, it explicitly prohibits running install, build, migration, or test commands in the Universal Rules.
- Sanitization: No explicit sanitization or filtering of external content is described before the agent processes the text.
Audit Metadata