directory-submissions
Fail
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references 'https://fitprofessionals.net', which is identified as a blacklisted malicious domain. Additionally, the skill's own files, specifically 'SKILL.md' and 'references/submission-tracker-template.csv', have been flagged for containing potentially malicious content by security scanners.\n- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using 'curl' to verify live links. This functionality can be exploited to perform Server-Side Request Forgery (SSRF) or other unauthorized network operations if the provided URLs are not properly sanitized or validated.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted user-supplied product descriptions and marketing context from external files.\n
- Ingestion points: User-provided product information and the marketing context read from '.agents/product-marketing.md'.\n
- Boundary markers: The skill does not implement boundary markers or instructions to isolate and ignore potentially malicious embedded content within the ingested data.\n
- Capability inventory: The agent is instructed to perform network operations using shell commands like 'curl' to interact with external web directories.\n
- Sanitization: No sanitization or validation protocols are established to filter out malicious payloads from the input data before it is processed.
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