The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the open web via Perplexity search results and AI-synthesized research summaries. Maliciously crafted content on the web could attempt to override agent instructions or exfiltrate data.
Ingestion points: Results returned by scripts/mcp/perplexity_search.py as described in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the search results are documented.
Capability inventory: The skill has access to the Bash tool for command execution and the Read tool for file system access.
Sanitization: No specific filtering, validation, or sanitization of external content is mentioned.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a local Python script (scripts/mcp/perplexity_search.py) using the uv runner. This is the primary intended mechanism for performing searches.

perplexity-search