create-release

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute "project tooling" and "release-relevant project gates" found within the target repository. This allows for the execution of arbitrary scripts or binaries present in the codebase being processed.
  • [INDIRECT_PROMPT_INJECTION]: The agent is directed to read and process data from external sources that could contain malicious instructions.
  • Ingestion points: The skill ingests content from "unreleased conventional commits," repository "workflows," and "release documentation."
  • Boundary markers: There are no explicit delimiters or instructions provided to prevent the agent from following commands embedded within this processed data.
  • Capability inventory: The agent utilizes git, the GitHub CLI (gh), and arbitrary local project tools.
  • Sanitization: The skill does not mention any validation or filtering of the content retrieved from commits or documentation files.
  • [EXTERNAL_DOWNLOADS]: The skill requires active network access to interact with the GitHub API and to publish artifacts to external package registries, which are not restricted to a specific whitelist.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 09:39 AM
Security Audit — agent-trust-hub — create-release