generate-release-notes

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local script located at tools/generate-release-notes.py. This script is part of the repository's internal toolset for processing commit history and metadata.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external sources.
  • Ingestion points: The Python script fetches PR details including titles, descriptions, and labels via the GitHub GraphQL API, which are then processed by the agent in Step 3 and Step 4 of the SKILL.md instructions.
  • Boundary markers: There are no explicit delimiters or instructions to the agent to ignore or treat the fetched PR content as non-instructional data.
  • Capability inventory: The skill allows the agent to use Bash, Write, Edit, and Grep tools across all project files.
  • Sanitization: The instructions do not specify any validation or sanitization of the content fetched from GitHub before it is presented to the agent for analysis and sorting.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 07:09 PM
Security Audit — agent-trust-hub — generate-release-notes