The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The search functionality provided in lib/search.ts creates a surface for indirect prompt injection by ingesting untrusted data from an external API.
Ingestion points: The search function retrieves and returns result.choices[0].message.content from the Perplexity API.
Boundary markers: The implementation lacks delimiters or instructions to the agent to treat the API response as data rather than instructions.
Capability inventory: The skill allows the agent to use Write, Edit, and Bash tools, which increases the potential impact if a prompt injection attack were to occur through the search results.
Sanitization: There is no evidence of escaping, filtering, or validation of the content received from the external API.

perplexity-multi-env-setup