use-agent-context
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs authorized local file read and write operations within a specified directory (/Users/kian/wiki) to manage persistent agent context. These actions are consistent with the skill's stated purpose and do not exhibit malicious intent.
- [SAFE]: Indirect Prompt Injection Analysis: The skill reads from local wiki files that could contain information from various sources. While no explicit delimiters or sanitization steps are defined, the risk is minimal as it targets the user's personal context directory.
- Ingestion points: /Users/kian/wiki/AGENTS.md, /Users/kian/wiki/context.md, and /Users/kian/wiki/notes.md
- Boundary markers: None explicitly defined; instructions direct the agent to prioritize live user evidence.
- Capability inventory: Local file reading and updating in the designated wiki directory.
- Sanitization: No specific filtering or escaping is implemented for the content read from the local files.
Audit Metadata