The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it ingests and analyzes content from untrusted external sources.
Ingestion points: The skill uses WebFetch and WebSearch to retrieve articles and search results from the internet.
Boundary markers: There are no defined delimiters or instructions (e.g., XML tags or clear separation) to help the agent distinguish between its instructions and the data fetched from external sources.
Capability inventory: The skill has access to Write, Read, Grep, and Glob tools. If an injection attack from a malicious website succeeds, the agent could be manipulated into reading, modifying, or writing files in the local environment.
Sanitization: There is no mention of filtering, escaping, or validating the content retrieved from WebFetch or WebSearch before the agent processes it for post creation.

social-post