atlas
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill functions as an orchestrator that passes user-provided arguments and retrieved external content to sub-components, which is an architectural pattern vulnerable to indirect prompt injection.
- Ingestion points: Data is ingested through the {{args}} parameter as well as through output from the Read, WebFetch, and WebSearch tools.
- Boundary markers: The skill instructions do not provide delimiters or instructions to the agent to ignore potentially malicious directions embedded in external data.
- Capability inventory: The skill is configured with access to tools including Bash, Write, and WebFetch, which can be leveraged if the agent is influenced by injected instructions.
- Sanitization: The routing logic forwards input to sub-skills without applying validation or filtering to the content.
Audit Metadata