release-notes-writer
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
gitandgh(GitHub CLI) commands to retrieve repository metadata, commit history, and pull request details. These commands are standard for software development workflows and aligned with the skill's primary purpose. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted text from external sources.
- Ingestion points: The workflow reads commit messages, PR titles, and PR descriptions via
git logandgh pr viewcommands (SKILL.md). - Boundary markers: No specific delimiters or "ignore instructions" warnings are used to isolate the fetched git/PR content from the agent's core instructions.
- Capability inventory: The skill possesses the ability to execute subprocess commands like
gitandghand then process the resulting text via an LLM to generate categorized release notes (SKILL.md). - Sanitization: No sanitization or filtering of the fetched text is performed before the AI processes it for summarization.
Audit Metadata