The Agent Skills Directory

[SAFE]: The skill provides marketing and copywriting guidelines for selecting and arranging customer testimonials. No executable code, scripts, shell commands, or network operations were found in the provided files.
[NO_CODE]: No code or scripts were detected in SKILL.md or test-prompts.json. The skill is entirely text-based documentation.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external text (customer testimonials). This presents a theoretical surface for indirect prompt injection if the feedback provided to the agent contains hidden instructions. However, because the skill has no dangerous capabilities such as file system writes, network exfiltration, or shell execution, the actual risk is negligible. Ingestion points: Customer feedback and testimonial text processed by the agent in SKILL.md. Boundary markers: None. Capability inventory: No dangerous capabilities found. Sanitization: None.

customer-testimonial