link-rot-detection
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow for extracting and processing external links from untrusted markdown files using system tools.
- Ingestion points: Markdown content sets (.md and .mdx files) as defined in the coverage section.
- Boundary markers: The instructions lack explicit delimiters or guidance to ignore malicious instructions embedded in the links being processed.
- Capability inventory: The frontmatter specifies the use of Read, Grep, and Bash tools, which are used to perform the described extraction and auditing tasks.
- Sanitization: The verification and coverage sections do not include requirements for sanitizing or validating the extracted URLs before they are used in potentially dangerous operations like shell-based network requests.
Audit Metadata