The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites (user-provided URLs and competitor domains) and processes this content to generate an SEO report. This external data is untrusted and could contain malicious prompts designed to influence the agent's behavior during the synthesis phase.
Ingestion points: Website content is cataloged via site-content-catalog and analyzed via seo-domain-analyzer and seo-traffic-analyzer (SKILL.md, Phase 1 & 2).
Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are defined for the analysis phase.
Capability inventory: The skill executes local Python and Node.js scripts and writes output to the filesystem.
Sanitization: There is no evidence of sanitization for the scraped content before it is processed by the AI.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands to run local scripts for site cataloging and SEO analysis.
Evidence: Phase 1 uses python3 skills/site-content-catalog/scripts/catalog_site.py. Phase 2 uses node skills/seo-domain-analyzer/src/cli.js analyze and python3 skills/seo-traffic-analyzer/scripts/analyze_seo.py.

seo-opportunity-finder