The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes untrusted data from an external source (rustman.org) and incorporates it into the agent's context to synthesize answers. This creates a surface where malicious instructions embedded in the external wiki content could influence agent behavior.
Ingestion points: Fetches index from https://rustman.org/llms.txt and content from https://rustman.org/wiki/{slug} using WebFetch.
Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to ignore instructions found within the fetched content.
Capability inventory: Uses WebFetch for networking and Read, Grep, and Glob for local filesystem access within the repository.
Sanitization: Absent. There is no evidence of filtering or escaping logic applied to the external content before prompt interpolation.
[EXTERNAL_DOWNLOADS]: The skill is configured to fetch remote content from rustman.org. This domain is identified as a vendor-owned resource belonging to the author 'fortunto2'. The operations are limited to fetching text-based documentation and do not involve the installation of unverified packages or the execution of remote scripts.

solo-knowledge