The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs and synthesizes responses without employing boundary markers or sanitization, creating a surface where malicious instructions in the source content could influence the agent's behavior.
Ingestion points: Content is fetched from https://rustman.org/llms.txt and https://rustman.org/wiki/{slug} via the WebFetch tool, as specified in SKILL.md.
Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded instructions when processing the fetched text.
Capability inventory: The skill uses WebFetch, Read, Grep, and Glob tools, enabling it to access both remote URLs and local files.
Sanitization: Absent. The skill does not perform any validation or filtering on the retrieved information before synthesis.
[EXTERNAL_DOWNLOADS]: The skill relies on fetching content from an external domain, rustman.org, to populate its knowledge base.
[COMMAND_EXECUTION]: The documentation in SKILL.md includes a curl command to manually update the local references/llms-snapshot.txt file and uses Grep for searching local files in offline mode.

solo-knowledge