The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation, templates, and strategy guides for social media management. No automated command execution, network requests, or data exfiltration mechanisms were detected within any of the provided files.
[INDIRECT_PROMPT_INJECTION]: The skill instructions include a prompt to read from local files such as .agents/product-marketing-context.md. While this constitutes a data ingestion point, the skill possesses no capabilities (such as network access or shell execution) that would allow for exploitation if the content of that file were malicious. The risk is assessed as minimal and typical for context-aware agents.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation patterns were found. All referenced external tools (e.g., Apify, CapCut, ElevenLabs) are mentioned as suggestions for the user to use manually and are not invoked by the skill itself.

social-content