The Agent Skills Directory

[SAFE]: The skill is comprised exclusively of markdown and JSON files providing guidance on social media strategy. It contains no executable scripts, binaries, or environment-modifying commands.- [PROMPT_INJECTION]: The skill instructions include a potential surface for indirect prompt injection via the ingestion of project context. Evidence chain: (1) Ingestion points: SKILL.md (reads .agents/product-marketing-context.md). (2) Boundary markers: Absent. (3) Capability inventory: No subprocess calls, network access, or file-write operations are present in any skill files. (4) Sanitization: Absent. The absence of dangerous capabilities renders this ingestion point safe.- [COMMAND_EXECUTION]: No shell commands, privilege escalation techniques, or dynamic context injections (e.g., !command syntax) were detected during the audit of the skill instructions or reference materials.- [EXTERNAL_DOWNLOADS]: The skill does not perform any remote downloads or code execution. References to third-party tools such as Apify or Descript are provided strictly as informational recommendations for the user.

social-content