gist-management
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill provides a markdown-based interface and tool definitions for interacting with an external GitHub MCP server. No scripts (Python, JavaScript, or Shell) are included in the skill definition.
- [SAFE]: The requirement for a GITHUB_TOKEN is a legitimate configuration step for the intended functionality (accessing the GitHub Gists API) and does not involve hardcoded credentials.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the ingestion of external data.
- Ingestion points: File contents retrieved from GitHub via the
gist_gettool. - Boundary markers: None specified; instructions do not advise the agent to ignore commands found within gist files.
- Capability inventory: The skill can create, update, and delete gists (write/delete access).
- Sanitization: No sanitization or validation of the external content is performed before it enters the agent's context.
Audit Metadata