The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using sqlmap. It provides templates for various execution modes including URL-based testing (-u), request-file parsing (-r), and automated batch processing (--batch).
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and processing data from external sources, which presents a surface for indirect prompt injection attacks.
Ingestion points: The skill reads user-supplied HTTP request files (req.txt) and processes HTTP responses (headers and body) from remote web servers targetted during injection testing.
Boundary markers: None identified. There are no instructions or delimiters provided to the agent to distinguish between the tool's output and potentially malicious instructions embedded in the target's HTTP responses.
Capability inventory: The agent is granted the capability to run sqlmap, which can perform network operations, file system reads (via the -r flag), and potentially achieve code execution on remote targets (via the --os-shell flag).
Sanitization: There is no mention of sanitizing or validating the content retrieved from remote targets before the agent processes the results.

tools-sqlmap