linkup
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses the 'orth' command-line tool, which is associated with the skill's author (orthogonal-sh), to perform its primary function of searching the web and fetching webpage content. All operations are consistent with the stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to fetch untrusted content from the internet, which inherently creates a surface for indirect prompt injection where an attacker could embed malicious instructions on a webpage to influence the agent's behavior.
- Ingestion points: External webpage content retrieved from the /search and /fetch endpoints in SKILL.md.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are provided in the skill text for handling untrusted data.
- Capability inventory: The skill utilizes the 'orth' CLI to perform web operations; no local shell access, file-system modification, or network exfiltration logic is present in the skill definition.
- Sanitization: No sanitization or validation of the fetched content is specified within the skill instructions.
Audit Metadata