The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches external documentation and code examples, creating a surface for potential indirect prompt injection if the source content contains malicious instructions.
Ingestion points: Data retrieved via the query-docs tool (SKILL.md).
Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or ignore instructions within the fetched documentation.
Capability inventory: The skill allows calling resolve-library-id and query-docs via the mcpc client; the impact depends on other tools available to the agent.
Sanitization: No specific sanitization or filtering logic is defined for the external documentation content.
[SAFE]: The skill implements security best practices by explicitly instructing the agent to never include API keys, passwords, or sensitive data in search queries.

context7