changelog-composer
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands like
git logandgh pr listto gather data from the local repository environment.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of untrusted commit messages and PR descriptions.\n - Ingestion points: Raw text from git logs and GitHub PR lists in
SKILL.md.\n - Boundary markers: The instructions do not define delimiters or specific constraints to prevent the agent from following directives contained within the parsed text.\n
- Capability inventory: The skill has access to shell command execution for git and GitHub CLI operations.\n
- Sanitization: There is no specified mechanism for sanitizing or escaping the input data before it is interpreted by the model.
Audit Metadata