The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it extracts and analyzes untrusted data from local files without sanitization or boundary markers.
Ingestion points: The agent reads content from titles, H1/H2 headings, and first paragraphs of files matching **/*.md, **/*.mdx, and **/*.html using the Read and Grep tools.
Boundary markers: There are no specified delimiters or instructions to ignore potential commands embedded in the processed text.
Capability inventory: The skill has access to Read, Grep, Glob, and WebFetch tools.
Sanitization: Extracted content is not sanitized or filtered before being passed to the language model for semantic analysis.
[DATA_EXFILTRATION]: The skill performs network operations to the DataForSEO API.
It uses WebFetch to interact with api.dataforseo.com, which is a well-known service provider for SEO data.
Credential management follows best practices by instructing the user to store the API login and password in environment variables rather than hardcoding them.

blog-cannibalization