content-quality-auditor

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Processing of External Data: The skill is designed to analyze documents and artifacts provided by the user or retrieved from connected sources, which represents a data ingestion surface.
  • Ingestion points: Artifacts provided by the user or accessed via connected sources as defined in SKILL.md.
  • Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions that may be embedded within the source documents.
  • Capability inventory: The skill's functionality is limited to generating markdown-based audit reports. It does not utilize tools for network communication, file system modifications, or arbitrary command execution.
  • Sanitization: The instructions do not specify any filtering or sanitization of external content before it is audited by the agent.
  • Security Consideration: While the ingestion of external data could theoretically allow for indirect prompt injection (where instructions in a document try to bias the audit), the impact is limited to the audit output itself. The lack of access to sensitive system capabilities effectively mitigates broader security risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:55 PM
Security Audit — agent-trust-hub — content-quality-auditor