issue
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and processing external data from GitHub, which constitutes an indirect prompt injection attack surface.
- Ingestion points: Content is ingested via the 'gh issue view' command as described in SKILL.md.
- Boundary markers: No explicit delimiters or 'ignore' instructions are provided to separate the ingested issue body from the agent's primary instructions.
- Capability inventory: The skill utilizes the 'gh' CLI for GitHub resource management and performs temporary file writes to the local file system.
- Sanitization: The skill mitigates risks by mandating the use of the --body-file parameter instead of inline shell arguments, which prevents shell-level command injection. It also specifies the use of quoted heredocs to prevent unintended shell variable expansion during content generation.
Audit Metadata