The Agent Skills Directory

[SAFE]: The skill's primary function is to transform technical requirements into structured markdown documents. It does not perform unauthorized network operations, access sensitive credentials, or attempt to modify system settings.
[DATA_EXFILTRATION]: No sensitive file paths (e.g., .ssh, .aws, .env) or network exfiltration patterns were identified. The skill writes plans to a user-defined or default documentation directory.
[PROMPT_INJECTION]: The skill includes instructions to ingest external specifications which constitute untrusted data (Indirect Prompt Injection surface). However, the risk is mitigated by the highly rigid task structure and specific documentation requirements which constrain the agent's output behavior. No direct prompt injection or bypass attempts were found in the skill instructions.
[COMMAND_EXECUTION]: The skill describes commands for developers or subagents to run (e.g., pytest, git) as part of the implementation tasks but does not execute these commands directly at runtime during the planning phase.
[REMOTE_CODE_EXECUTION]: No remote code downloads or execution patterns (e.g., curl | bash) were detected.

writing-plans