ln-64-community-announcer
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which could contain instructions designed to influence the agent's behavior.\n
- Ingestion points: The skill reads remote Git history, documentation, manifests, release notes, and source code diffs (SKILL.md).\n
- Boundary markers: No specific delimiters or wrapping techniques are prescribed to isolate external data from the skill's internal logic.\n
- Capability inventory: The agent can execute GitHub CLI commands, call GraphQL APIs, and create temporary files (SKILL.md).\n
- Sanitization: The risk is mitigated by requiring explicit user approval of the final announcement and recommending the escaping of API inputs.\n- [COMMAND_EXECUTION]: The skill uses the GitHub CLI to interact with the repository and discover information. This is a primary function for its intended use case.\n- [SAFE]: The skill correctly identifies and avoids the exposure of sensitive credentials such as repository tokens or node IDs in its public output. It relies on trusted services like GitHub for all external operations.
Audit Metadata