evo-archiving
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git statusandgit diff --stat(SKILL.md) to identify changes in the project. These are standard development tools and are used here within the expected workflow. - [PROMPT_INJECTION]: There is an indirect prompt injection surface as the skill reads untrusted data from project files such as
docs/architecture.mdanddocs/ledger.jsonl(SKILL.md). Ingestion points: documentation reading and git diff analysis. Boundary markers: Absent. Capability inventory: File system read/write and git command execution. Sanitization: Absent. The skill mitigates risks by requiring user confirmation before finalizing any documentation updates.
Audit Metadata