claw-release

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the execution of system binaries (bash, git, jq, gh) and a local script (./scripts/release-skill.sh) to automate the release process.
  • [DATA_EXFILTRATION]: The workflow involves pushing commits and tags to remote GitHub repositories and creating releases, which is the expected primary purpose of a release management tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from other skill files to automate metadata updates, creating a surface for indirect instruction processing.
  • Ingestion points: Reads version information and metadata from skill.json and SKILL.md files.
  • Boundary markers: No explicit delimiters are used to wrap data ingested from external files.
  • Capability inventory: Possesses the ability to perform git operations (commit, tag, push) and create GitHub releases via CLI.
  • Sanitization: Content is parsed for versioning but no explicit sanitization or validation of the ingested strings is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 03:49 PM