no-ai-slop
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted text provided by the user (drafts for editing or auditing), which could potentially contain malicious instructions.
- Ingestion points: User drafts are ingested in the
EditandDetectworkflows defined inSKILL.md. - Boundary markers: The instructions lack explicit requirements for the user or agent to use delimiters (like code blocks or specific tags) to separate the untrusted draft from the agent's internal instructions.
- Capability inventory: The agent is authorized to edit text, create HTML artifacts, and invoke the
release-videoskill. It does not have access to sensitive local files or arbitrary shell execution. - Sanitization: No sanitization or filtering of the user-provided draft is specified before the agent processes it.
Audit Metadata