Skills
Navigate
skills/whyashthakker/agent-skills-marketing/generative-engine-optimisation-geo/Gen Agent Trust Hub

generative-engine-optimisation-geo

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites during its audit workflow, creating a surface for indirect prompt injection attacks.
  • Ingestion points: The skill uses scripts/seo_audit.py and curl commands in SKILL.md to fetch content from arbitrary user-provided URLs.
  • Boundary markers: There are no explicit delimiters or boundary markers defined in the instructions to help the agent distinguish between its instructions and the retrieved external content.
  • Capability inventory: The skill operates with Read and Write permissions and utilizes shell-level tools like curl and python3 for network and script execution.
  • Sanitization: The seo_audit.py script performs basic metadata extraction but does not sanitize the content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill's primary workflow involves executing shell commands, including curl for fetching web data and python3 for running auditing scripts such as seo_audit.py and various DataForSEO API integration scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:38 PM