antislop-audit
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for auditing, which is an ingestion point for untrusted data. This creates a surface for indirect prompt injection where an attacker might embed instructions within the text being audited.
- Ingestion points: The text supplied by the user to the agent for slop analysis (SKILL.md).
- Boundary markers: The skill contains an explicit 'Core rule' instructing the agent to treat audited text as untrusted data and to ignore any embedded commands or role-play requests.
- Capability inventory: The skill is limited to text analysis and reporting; there are no instructions for file system writes, network requests, or command execution.
- Sanitization: The agent is instructed to only flag patterns and ignore any executable content within the input.
Audit Metadata