The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or sensitive data exposure was detected. The skill primarily consists of instructional content for users and the agent.
[COMMAND_EXECUTION]: Includes an example command (npx skills add sales-skills/sales --skills sales-do) to install a related skill from the same vendor, which is consistent with the skill's documented purpose.
[PROMPT_INJECTION]: The skill implements a persistent learning mechanism via references/learnings.md, which was analyzed for indirect prompt injection risk.
Ingestion points: Reads from references/learnings.md at initialization to gather accumulated context (Step 1).
Boundary markers: No explicit delimiters or boundary markers are used to isolate the learned content.
Capability inventory: The skill is instructed to write new observations to references/learnings.md (Self-improving section).
Sanitization: No explicit sanitization or validation of the content appended to the file is performed.

sales-microlaunch