The Agent Skills Directory

[SAFE]: The skill's primary function is project management and documentation using local markdown files, with no evidence of malicious intent or unauthorized actions.
[INDIRECT_PROMPT_INJECTION]: The skill proactively mitigates risks from untrusted data in plan files by instructing the agent to maintain user goals in their original wording and to explicitly label any agent-proposed changes or interpretations as unconfirmed until approved by the user.
[DATA_EXFILTRATION]: No network exfiltration patterns or unauthorized data access were identified. The skill respects project boundaries and resource limits, requiring user permission for significant data transfers or external writes.

work-plan