The Agent Skills Directory

[SAFE]: The skill implements a standard documentation generation workflow. No suspicious commands, network exfiltration patterns, or obfuscated contents were identified.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted conversation context and repository information. 1. Ingestion points: Conversation history and codebase state (referenced in SKILL.md). 2. Boundary markers: None explicitly defined to separate untrusted context from instructions. 3. Capability inventory: Ability to publish text content to an external project issue tracker. 4. Sanitization: Relies on the model's internal safety guardrails.

to-prd