skills/basmilius/skills/release-notes/Gen Agent Trust Hub

release-notes

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data sourced from git commit messages and file diffs. A malicious actor with commit access to the target repository could attempt to embed prompt injection strings in commit subjects to influence the agent's output during the generation of release notes.
  • Ingestion points: The skill instructs the agent to ingest external data via git log, git diff, and git show in Steps 2 and 3 of SKILL.md.
  • Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore instructions embedded within the commit messages.
  • Capability inventory: The skill utilizes bash, git, gh, and sed to perform its operations.
  • Sanitization: Absent. There is no explicit filtering or sanitization of the commit data before it is processed by the LLM.
  • [COMMAND_EXECUTION]: The skill performs shell command execution using standard development tools (git, gh, sed). These commands are scoped to the project directory and are used for read-only operations (fetching tags, viewing diffs) consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 12:26 AM
Security Audit — agent-trust-hub — release-notes