The Agent Skills Directory

[SAFE]: The skill provides marketing strategies and templates for social media platforms. It operates as a purely instructional tool with no associated executable code or script files.\n- [SAFE]: No external dependencies, remote code execution, or network communication patterns were detected. References to third-party tools like Apify and Phantom Buster are informational for user guidance and not automated by the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to ingest external data from .claude/product-marketing-context.md and social media content for analysis. Evidence chain: 1. Ingestion points: .claude/product-marketing-context.md and content for reverse engineering. 2. Boundary markers: Absent. 3. Capability inventory: No high-risk tools or capabilities (subprocess, eval, network) are requested or defined. 4. Sanitization: Absent. The lack of sensitive capabilities renders this surface safe.\n- [METADATA_POISONING]: The metadata field updated contains a future date (2026-03-06), which is likely a placeholder or clerical error and does not affect the safety or capability assessment of the skill.

social-content