The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run local shell commands (ls, grep, cat) and a local shell script (./qa-playwright-capture.sh) to gather evidence and diagnostic information about a project's implementation.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted data, which creates a potential surface for indirect prompt injection.
Ingestion points: Content fetched from http://localhost:8000, directory listings of resources/views/, and the contents of user-controlled files including *.html, *.css, *.blade.php, and test-results.json (found in SKILL.md).
Boundary markers: None present; the instructions do not establish clear delimiters or use "ignore embedded instructions" warnings for the external data being analyzed.
Capability inventory: The skill possesses the ability to execute shell commands and invoke a local shell script based on the analysis of these files.
Sanitization: No sanitization, validation, or escaping of the ingested external content is specified before the agent processes it for the final report.

evidence-collector