evidence-collector

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell script named ./qa-playwright-capture.sh and standard shell utilities such as ls, grep, and cat to verify the codebase and capture visual evidence.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes the content of various files (HTML, CSS, Blade templates) and JSON test results from the local environment to perform its analysis. These files could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: resources/views/, *.html, *.css, *.blade.php, and public/qa-screenshots/test-results.json.
  • Boundary markers: None identified; the agent reads raw file content.
  • Capability inventory: Access to bash, git, and file system operations.
  • Sanitization: No explicit sanitization or validation of the ingested file content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:51 PM
Security Audit — agent-trust-hub — evidence-collector