The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown focused on influencer marketing strategies. It does not include any code, scripts, or tool invocations.
[INDIRECT_PROMPT_INJECTION]: The skill contains instructions to read project context files which could potentially contain untrusted data.
Ingestion points: Reads .claude/project-context.md or .cursor/project-context.md in the Initial Assessment section.
Boundary markers: None present.
Capability inventory: The skill possesses no capabilities for subprocess execution, file writing, or network operations.
Sanitization: None present.
Conclusion: Because the skill lacks any active capabilities or tool access, the ingestion of untrusted context data does not pose a functional security risk.

influencer-marketing