etsy-tony-full

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content such as Etsy product links, descriptions, and images. This content is potentially attacker-controlled (e.g., from a competitor's listing) and could contain malicious instructions to subvert the agent's behavior.
  • Ingestion points: The skill explicitly prompts for product photos, links, copy, or specific questions in SKILL.md and workflow-map.md.
  • Boundary markers: There are no instructions or delimiters provided to the agent to treat this ingested content as untrusted data or to ignore any instructions embedded within it.
  • Capability inventory: The skill has the capability to write files to the local filesystem (./etsy-output) and execute a local Python script (scripts/list_skills.py).
  • Sanitization: No sanitization or filtering of the external input is specified in the prompt instructions.
  • [COMMAND_EXECUTION]: The skill provides instructions to execute a local script scripts/list_skills.py via the command line to discover available capabilities.
  • Evidence: Found in SKILL.md under the '选择最小可用入口' section. The script itself is provided in the skill package and contains safety checks to prevent path traversal outside the skill's root directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 02:56 PM