The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute the git log command to retrieve repository history. This is the primary and expected function of the tool.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes git commit messages, which are external data that could contain malicious instructions. 1. Ingestion points: Commit messages retrieved via git log as described in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Command execution (git log) mentioned in SKILL.md. 4. Sanitization: No explicit sanitization of commit messages is mentioned.

changelog-generator