gh-oss-release

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and the oss-watch extension to perform repository operations, such as fetching commit history, creating releases, and triggering automated workflows.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted commit messages from external repositories to influence its version recommendation logic. Ingestion points: Commit messages retrieved via gh api in Step 2 of SKILL.md. Boundary markers: No delimiters or instructions are used to isolate the commit content from the agent's instructions. Capability inventory: The skill can create GitHub releases and trigger repository workflows as described in Steps 5 and 7. Sanitization: The skill does not perform any validation or sanitization of the fetched commit strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 02:44 AM