trend-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill's metadata specifies a non-existent model 'gpt-5.6-terra'. This is misleading metadata that misrepresents the execution environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external signals from ecosystems and implementations, which creates a surface for indirect prompt injection if those sources contain malicious instructions.
- Ingestion points: Data collection during the 'Working mode' in SKILL.md.
- Boundary markers: None present; the skill does not specify how to delimit or ignore instructions within external data.
- Capability inventory: None; the skill does not define its own tools or scripts with file or network access.
- Sanitization: None; there are no instructions to validate or filter the ingested signals.
Audit Metadata