The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill contains instructions for reading and processing external data from reconnaissance files (e.g., urls.txt), which constitutes an attack surface for indirect prompt injection.
Ingestion points: The skill instructs the agent to read reconnaissance data using commands like cat recon/$TARGET/urls.txt.
Boundary markers: There are no explicit boundary markers or instructions to treat the content of the external files as untrusted data.
Capability inventory: The skill utilizes common command-line utilities such as grep, base64, gzip, and xmllint to process the ingested data.
Sanitization: No sanitization or validation steps are provided for the content read from the reconnaissance files, allowing potentially malicious instructions embedded in the data to be processed by the agent.

hunt-saml