bio-link-deployer
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data provided by the user (such as
user_name,tagline, andlinks) and from previous conversation context to populate an HTML template. - Ingestion points: The skill ingests data through the input schema fields and by gathering URLs and labels from earlier stages of the conversation (S1-S4) as described in the workflow section of
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions that might be embedded within the user-provided link labels or taglines.
- Capability inventory: The skill's capabilities are restricted to generating and presenting HTML code to the user. It does not possess capabilities for arbitrary command execution, network exfiltration, or unauthorized file system access.
- Sanitization: The instructions do not explicitly mandate the sanitization or escaping of user-provided strings before they are interpolated into the
templates/bio-link.htmlfile. While this presents a theoretical surface for Cross-Site Scripting (XSS) in the generated file, it is an inherent aspect of the skill's primary purpose as a code generator and does not indicate malicious intent.
Audit Metadata