utility-pm-changelog-curator
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes git log output, which may contain untrusted commit messages from external contributors. These messages could potentially contain instructions aimed at influencing the agent's behavior during the drafting process.\n
- Ingestion points:
git logoutput (processed inSKILL.mdinstructions).\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat commit messages strictly as data.\n
- Capability inventory: The skill uses shell execution (
git log,git status) and file system access (readingCLAUDE.md,CHANGELOG.md).\n - Sanitization: Commit messages are not sanitized or escaped before being processed by the agent.\n- [DYNAMIC_EXECUTION]: For non-Claude clients, the skill dynamically loads its system prompt and operating instructions from the local file
agents/pm-changelog-curator.md.\n- [COMMAND_EXECUTION]: The skill requires shell execution capabilities to rungit log,git describe, andgit statusto retrieve repository history and metadata.
Audit Metadata