seo-content-homepage

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites and local files to generate marketing copy, which could allow malicious instructions embedded in those sources to influence the agent's behavior.
  • Ingestion points: The skill uses audit scripts (seo_audit.py, section_audit.py, page_benchmark.py) to fetch content from arbitrary URLs and reads local Markdown notes from an Obsidian vault.
  • Boundary markers: The instructions do not specify the use of delimiters or protective phrasing to isolate untrusted content from the agent's core logic.
  • Capability inventory: The skill is capable of executing shell commands (Python scripts) and writing to local files (Obsidian action log).
  • Sanitization: No explicit sanitization or filtering of the ingested data is mentioned in the instructions.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several local Python scripts using the python3 command. While these scripts are part of the skill's package, they are executed with user-supplied URL arguments, which involves shell-level interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 06:28 AM