markdown-crossref-validator
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted markdown files, which can contain hidden instructions intended to influence the agent's behavior. 1. Ingestion points: The skill reads markdown files to extract links and headings (SKILL.md, Step 1). 2. Boundary markers: Absent; there are no instructions provided to the agent to treat file content as untrusted or to ignore instructions found within. 3. Capability inventory: The skill utilizes file reading, directory listing, and grep-based parsing (SKILL.md, Tools to use). 4. Sanitization: Absent; the skill does not define methods to sanitize extracted text before use.
- [Command Execution] (SAFE): The skill suggests using standard tools like grep for text parsing. No patterns of insecure shell interpolation or user-input execution were detected.
- [Data Exposure & Exfiltration] (SAFE): File access is restricted to the intended purpose of validating project links, with no signs of credential harvesting or external data transmission.
Audit Metadata