sepia-write
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a wrapper designed to bind a specific 'write' operation from a sibling skill file. It does not perform any network operations, command execution, or file system modifications.
- [INDIRECT_PROMPT_INJECTION]: The skill acknowledges the risk of indirect prompt injection by explicitly instructing the agent to treat target content as untrusted data and not as instructions or authority.
- [DYNAMIC_EXECUTION]: The skill resolves a specific sibling path (
../sepia/SKILL.md) to load its logic. It includes strict constraints to prevent path traversal or searching in unauthorized directories, limiting the scope of its operation resolution.
Audit Metadata