The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected. The skill is purely instructional and guides the agent's behavior within its intended scope.
[NO_CODE]: The provided skill package contains only markdown instructions and configuration metadata. It does not include any executable scripts, binaries, or automated command-line operations.
[DATA_EXPOSURE]: The skill is designed to read local project documentation and git history to minimize user interviewing. This is functional behavior and is accompanied by strict instructional safeguards that explicitly forbid the extraction or persistence of sensitive data, such as credentials, account IDs, and PII.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface as it ingests untrusted local project files. However, the risk is mitigated because the skill's capabilities are limited to providing text-based recommendations and updating a local markdown context file, with no high-privilege tool execution involved.

advertising-kickoff