The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites to determine SEO triage actions, creating a surface for potential injection from scanned content.
Ingestion points: External web content fetched from the domain or URLs provided by the user via webfetch and dfs_client.py.
Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate external content from the agent's logic.
Capability inventory: The skill has the ability to execute shell commands (Python scripts) and write files to the local filesystem.
Sanitization: There is no mention of sanitizing or filtering the fetched content before the agent analyzes it or includes it in reports.
[COMMAND_EXECUTION]: The skill uses subprocess calls to execute local Python scripts (scripts/dfs_client.py and scripts/report_publish.py) with user-supplied arguments.
Evidence: python scripts/dfs_client.py ranked --target "<domain>" --limit 500 and python scripts/report_publish.py <report>.md.
[DYNAMIC_EXECUTION]: The skill generates reports and then dynamically executes a script (report_publish.py) that processes these generated files.
Evidence: Instructions to save reports to %SEO_REPORTS_DIR% and then run a publisher script on the resulting .md file.

thin-content-detector