on-page-seo
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes raw HTML content fetched from user-provided URLs, which introduces an attack surface for indirect prompt injection.
- Ingestion points: The skill performs a
webfetchof a user-provided target URL to retrieve raw HTML (SKILL.md). - Boundary markers (absent): There are no specific instructions or delimiters provided to the agent to treat the fetched HTML content as untrusted data or to ignore any potential instructions embedded within that HTML.
- Capability inventory: The skill has the ability to execute local Python scripts (
dfs_client.py,report_publish.py) and write files to the file system (ONPAGE-<slug>-<date>.md). - Sanitization (absent): No sanitization or filtering logic is specified for the raw HTML content before it is analyzed by the agent.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute Python scripts with arguments derived directly from user input.
- Evidence: The skill uses
python scripts/dfs_client.py onpage --url <url>andpython scripts/dfs_client.py serp --keyword "<target keyword>". - Risk: If the
<url>or<target keyword>provided by the user contains shell-sensitive characters, it could lead to command injection depending on how the underlying system handles the subprocess execution.
Audit Metadata