enterprise-ai-usecase-priority-assessment

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided business scenarios and content from external URLs provided by the user.
  • Ingestion points: Processes untrusted data via the aiStrategyLink and aiUsecaseListText parameters defined in SKILL.md and references/form-schema.json.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used to isolate untrusted input within the analysis pipeline.
  • Capability inventory: The skill possesses the capability to transmit processed data to an external API via the scripts/run.py execution script.
  • Sanitization: There is no evidence of validation or sanitization of the content retrieved from links or provided in text inputs before it is processed by the diagnostic engine.
  • [DATA_EXFILTRATION]: The skill sends user-provided diagnostic parameters and the user's AISKILLS_API_KEY to the external domain https://ai-skills.ai. This is the documented and intended functional behavior of the skill for performing remote diagnostics.
  • [COMMAND_EXECUTION]: The skill includes a standalone Python script (scripts/run.py) designed to be executed in the user's local environment to facilitate interaction with the vendor's API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:58 AM
Security Audit — agent-trust-hub — enterprise-ai-usecase-priority-assessment