The Agent Skills Directory

[SAFE]: The skill's instructions and metadata are consistent with its stated purpose of summarizing git commit logs. No evidence of malicious commands, credential harvesting, or unauthorized network activity was found.- [PROMPT_INJECTION]: The skill processes git commit history, which constitutes untrusted data, presenting a potential surface for indirect prompt injection. However, this is inherent to the tool's primary purpose and no exploitable capabilities were identified. Ingestion points: Git history (commit messages). Boundary markers: Absent. Capability inventory: Local repository access for log reading and text generation. Sanitization: Not defined in the prompt instructions.

changelog-generator