context-journal-tater
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read the entire session back-and-forth, creating an ingestion point for potentially malicious instructions embedded in previously processed data.
- Ingestion points: Full session conversation logs (SKILL.md, Procedure step 1).
- Boundary markers: None specified to differentiate between instructions and the data being reviewed.
- Capability inventory: File writing to 'context-journal/out/', web searching/fetching, and codebase inspection tools.
- Sanitization: No explicit logic is provided to sanitize or escape content found within the session history.
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to use web search and fetch tools to ground findings in official documentation and best practices (SKILL.md, Procedure step 4).
- [COMMAND_EXECUTION]: The skill is authorized to inspect the local codebase to verify anti-patterns, which involves the use of agent-level file system and search commands (SKILL.md, Procedure step 4).
Audit Metadata