content-auditor
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze external content drafts, which constitutes a surface for indirect prompt injection. Malicious instructions could potentially be embedded in the text provided for auditing to influence the agent's output.
- Ingestion points: The agent processes user-supplied text, drafts, and articles as defined in the skill scope.
- Boundary markers: There are no explicit instructions to use delimiters or security-focused boundary markers to isolate the untrusted content from the system instructions.
- Capability inventory: The skill is purely analytical and does not invoke tools for file system writing, network requests, or shell command execution.
- Sanitization: No specific sanitization or filtering logic is defined for the input content.
- [SAFE]: The skill does not perform any network operations, download external dependencies, or attempt to persist across sessions.
- [SAFE]: No obfuscation, hidden characters, or suspicious metadata patterns were detected in the skill files.
Audit Metadata