atb-aclnn-operator-replacement-designer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates a workflow where the agent fetches and analyzes content from user-provided external URLs to generate local design documents and drive file system operations.
- Ingestion points: Untrusted documentation content is ingested from external URLs provided by the user, as specified in the 'Interface Document Analysis' phase of
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions that might be embedded within the fetched documentation.
- Capability inventory: The skill is granted access to tools including
Write,Edit,Bash, andReadfor repository analysis and file generation. This combination of untrusted input and local write/execution capabilities creates an exploitable attack surface. - Sanitization: The skill does not implement or describe any sanitization or validation logic for content retrieved from external sources before processing it.
Audit Metadata