testing-evidence-collector
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
./qa-playwright-capture.shto generate visual evidence. It also utilizes standard utilities likels,grep, andcatfor file system inspection and reading test results. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes untrusted data from the project files being tested (HTML, CSS, and JSON files). An attacker could embed malicious instructions in these files to influence the agent's behavior.
- Ingestion points: Reads files from
resources/views/,*.html, andpublic/qa-screenshots/test-results.json. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The skill has the ability to execute shell commands and local shell scripts.
- Sanitization: There is no evidence of input validation or content escaping before the ingested data is processed.
Audit Metadata