directory-submissions
Fail
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes a reference to the URL
https://fitprofessionals.netwithin the directory list reference files. This domain is currently blacklisted and flagged as malicious by URL scanners. - [METADATA_POISONING]: The
SKILL.mdfile contains several deceptive statements using future dates, such as corporate acquisitions in 2026 and historical changes in 2025. This misinformation can pollute the agent's knowledge base and mislead users regarding the skill's context and recency. - [INDIRECT_PROMPT_INJECTION]: The skill instructions allow for the ingestion of product marketing context from files like
.agents/product-marketing.md, which provides an attack surface for indirect prompt injection. 1. Ingestion points: The skill reads from local marketing context files. 2. Boundary markers: The skill does not use delimiters to wrap the external data or provide instructions to ignore embedded commands. 3. Capability inventory: While the skill reads untrusted data, its capabilities are restricted to text generation and no high-risk tools are automatically executed on the data. 4. Sanitization: The skill does not implement validation or sanitization for the ingested marketing data.
Recommendations
- CRITICAL: 2 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata