The Agent Skills Directory

[SAFE]: The skill provides legitimate marketing instructions and frameworks for influencer outreach, deal structuring, and ROI measurement. No malicious patterns or security risks were identified.
[SAFE]: The instructions explicitly mandate compliance with legal disclosure requirements (FTC guidelines), ensuring that all partnerships, including gifting and volume-based creator programs, are conducted transparently. The skill proactively addresses and corrects potential legal violations in its reference materials.
[INDIRECT_PROMPT_INJECTION]: The skill processes marketing context from local files, which is a standard surface for indirect prompt injection.
Ingestion points: Processes .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md to inform partner-fit decisions.
Boundary markers: Absent; the skill instructs the agent to read these files as ground truth without specific isolation markers or instructions to ignore embedded commands.
Capability inventory: Utilizes tool-based capabilities for content fetching (social-fetch) and video analysis (watch-video).
Sanitization: No explicit sanitization or filtering of external context file content is defined in the instructions.

influencer-marketing