compliance-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
grep) and internal Python scripts (e.g.,scripts/check_gdpr.py,scripts/validate_hipaa.py) to perform compliance checks and evidence collection from the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an inherent vulnerability to indirect prompt injection as it is designed to analyze untrusted external data.
- Ingestion points: The agent analyzes user-provided files including JSON, YAML, and Markdown within the
config/,policies/, andprocedures/directories (inSKILL.md). - Boundary markers: There are no explicit instructions to the agent to treat data from these files as untrusted or to ignore any potential embedded instructions.
- Capability inventory: The skill enables the agent to execute shell commands and internal Python scripts based on the analysis of these files (in
SKILL.md). - Sanitization: The skill does not describe or implement any sanitization or validation of the content processed from external files.
Audit Metadata