ghpm-view
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from GitHub Projects, creating a potential surface for indirect prompt injection if project content is maliciously crafted.
- Ingestion points: Project item titles, field values, and assignees are fetched via the GitHub CLI as part of the data resolution and filtering phases.
- Boundary markers: The workflow does not define delimiters or specific instructions to isolate retrieved project data from the agent's context.
- Capability inventory: The skill utilizes Bash (specifically restricted to gh CLI commands), Read, and Grep for data retrieval and processing.
- Sanitization: No logic for sanitizing or escaping the retrieved content is mentioned in the formatting or processing instructions.
Audit Metadata