The Agent Skills Directory

[SAFE]: The skill provides a legitimate academic framework for PhD-level qualitative research. It guides the agent through methodologies like Grounded Theory and Thematic Analysis without including executable code or dangerous instructions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external qualitative data, which establishes a potential surface for indirect prompt injection. However, given this is the primary purpose of the skill and it lacks high-risk tools like shell execution or file writing, the risk is minimal.
Ingestion points: External data enters the agent's context through the listed tools WebFetch, Read, Grep, and Glob used for qualitative extraction.
Boundary markers: The skill does not define specific instruction-data boundary markers (e.g., XML tags or delimiters) to isolate research content from the analysis instructions.
Capability inventory: The skill's scope is restricted to search and retrieval tools (WebSearch, WebFetch, Read, Grep, Glob). It does not possess capabilities for network exfiltration, persistence, or privilege escalation.
Sanitization: There are no explicit sanitization or filtering instructions for the ingested text, as the focus is on verbatim qualitative analysis.

qualitative-research