The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its primary function involves ingesting and analyzing untrusted data from external sources to generate SEO diagnostics.
Ingestion points: External data enters the agent context through the materialUrl, materialFile, and materialText parameters as defined in references/form-schema.json and SKILL.md.
Boundary markers: There are no specific delimiters or instructions provided to the agent to prevent it from executing commands that might be embedded within the audited content.
Capability inventory: The skill's scripts are limited to making network requests to the designated API and do not possess capabilities for local file system modification or arbitrary command execution.
Sanitization: No input sanitization or filtering is performed on the data before it is sent to the processing API.
[EXTERNAL_DOWNLOADS]: The scripts/run.py script includes logic to import and utilize the certifi Python package to manage CA certificates for secure communication with the vendor's API endpoints.

ai-seo-audit