The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from research papers and web searches, creating a surface for indirect prompt injection.
Ingestion points: The skill reads content from reaper-workspace/papers/ and results from the arxiv.py and iacr.py scripts.
Boundary markers: There are no explicit delimiters or instructions to ignore commands found within external data.
Capability inventory: The skill can write to the local filesystem (investigation logs and results) and perform network searches.
Sanitization: No sanitization or validation logic is specified for ingested paper content.
[EXTERNAL_DOWNLOADS]: Fetches research papers from well-known scientific repositories including arXiv and IACR.
[COMMAND_EXECUTION]: Executes local search scripts arxiv.py and iacr.py to facilitate literature review.

investigate