Skills
Navigate
skills/ssmasrour/marketingskills/directory-submissions/Gen Agent Trust Hub

directory-submissions

Fail

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The directory database in references/directory-list.md and references/submission-tracker-template.csv includes https://fitprofessionals.net, which is flagged as malicious by automated scanners.
  • [COMMAND_EXECUTION]: The instructions in SKILL.md direct the agent to execute shell commands (curl) to verify outbound links on directories. This capability allows the agent to interact with the flagged malicious URL.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from .agents/product-marketing.md and user-provided product details without using boundary markers, sanitization, or instructions to disregard embedded commands.
  • [DATA_EXPOSURE]: The workflow requires the agent to access and process internal product marketing files, which could lead to the unintended disclosure of sensitive strategic information during the directory submission process.
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
Risk Level
CRITICAL
Analyzed
Aug 22, 2026, 02:04 PM