no-ai-slop
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process user-provided text drafts, which creates a surface for indirect prompt injection if the user input contains malicious instructions.
- Ingestion points: Text drafts provided by the user are ingested into the agent context for editing and detection tasks, as described in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the user's draft.
- Capability inventory: The skill does not possess any dangerous capabilities; no file writing, network operations, or subprocess executions are defined or requested.
- Sanitization: There is no mention of sanitizing or escaping user input before it is processed by the agent.
- [SAFE]: The skill does not contain any hardcoded credentials, obfuscated URLs, or persistence mechanisms. It focuses entirely on stylistic editing principles and persona-based instructions.
Audit Metadata