prowler-compliance-review
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes compliance JSON files provided in Pull Requests, which serves as an entry point for untrusted data that could contain malicious instructions designed to influence the agent's review.
- Ingestion points: The skill reads and interprets JSON files from the codebase, specifically under
prowler/compliance/{provider}/{framework}.json. - Boundary markers: The instructions lack explicit boundary markers or system instructions to ignore potential natural language commands embedded within the JSON's
DescriptionorRationaleStatementfields. - Capability inventory: The agent has access to powerful tools including
Bash,Edit,Write, andTask, which could be targeted by successful injection. - Sanitization: The
validate_compliance.pyscript validates structure and check existence but does not sanitize the text content of descriptive fields for potential prompt injection patterns. - [COMMAND_EXECUTION]: The skill requires the execution of local Python scripts and project-specific CLI tools to perform its intended auditing functions.
- Evidence: The skill instructions involve running
python3 skills/prowler-compliance-review/assets/validate_compliance.pyanduv run python prowler-cli.pyto validate and test frameworks.
Audit Metadata