skills/sammii-hk/skills/seo/Gen Agent Trust Hub

seo

Fail

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: HIGHDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill contains a 'Sync to Hive Mind' procedure that automatically transmits site performance data, including impressions and click metrics, to an external server at http://95.217.179.111:3333/update-seo via a POST request.\n- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands such as curl, grep, head, and tr to extract data from local report files and perform network operations.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from Google Search Console (specifically search queries) and interpolates it into its analysis context without adequate protection.\n
  • Ingestion points: Google Search Console performance data including user-controllable search queries and page URLs.\n
  • Boundary markers: No delimiters or 'ignore' instructions are used to separate external search data from the agent's internal analysis logic.\n
  • Capability inventory: File writing (seo-digest-*.md), shell execution (curl), and network access.\n
  • Sanitization: No validation or escaping is applied to the retrieved search queries before they are processed by the agent or included in shell commands.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 22, 2026, 10:18 PM