project-archive-done
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external GitHub project items, which could introduce untrusted content into the agent's context.
- Ingestion points: External data enters the agent context via the
gh project item-listcommand execution described in Step 2 ofSKILL.md. - Boundary markers: No explicit delimiters or instructions are used to segregate the retrieved external item data from the agent's internal prompt context.
- Capability inventory: The skill possesses the capability to modify project data via
gh project item-archivein Step 6 ofSKILL.md. - Sanitization: There is no implementation of content sanitization or verification to filter or escape potentially malicious text contained within item fields.
Audit Metadata