content-quality-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands (
git rev-parse --show-toplevel) to locate the project root and executes local Python scripts (rubric-score.py,validate-audit-artifact.py) to process audit data and validate artifacts. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and analyze content from user-provided URLs, which introduces a surface for indirect prompt injection attacks. Ingestion points: External content is fetched using the
WebFetchtool. Boundary markers: The instructions explicitly mandate treating fetched page text, metadata, and comments as untrusted evidence. Capability inventory: The skill combines network fetching, shell command execution, and local file writing capabilities. Sanitization: The mitigation strategy relies on instructional guardrails to treat data as untrusted, without providing specific programmatic sanitization logic in the analyzed files.
Audit Metadata