The Agent Skills Directory

[SAFE]: The skill consists exclusively of instructional documentation and markdown guidelines. It does not include executable scripts, binaries, or automated configuration changes.
[SAFE]: No evidence of prompt injection, obfuscation techniques, or unauthorized data access patterns was found.
[INDIRECT_PROMPT_INJECTION]: The skill defines procedures for fetching external web content via Perplexity tools, which creates an attack surface for indirect prompt injection from third-party websites.
Ingestion points: Tool outputs from mcp__perplexity__perplexity_search and mcp__perplexity__perplexity_ask described in SKILL.md.
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or specific safety framing when processing the search results.
Capability inventory: The skill does not implement any capabilities itself; it provides instructions for using external search tools.
Sanitization: No sanitization or filtering logic is specified within the skill instructions.

perplexity