deep-research
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the internet while possessing powerful local capabilities.
- Ingestion points: The skill methodology in SKILL.md uses WebSearch and WebFetch tools to bring external web content into the agent context.
- Boundary markers: The instructions in SKILL.md do not provide delimiters or safety warnings to isolate or ignore potentially malicious instructions embedded in the retrieved web data.
- Capability inventory: The agent has access to the Bash, Read, Grep, and Glob tools as specified in the SKILL.md allowed-tools field, enabling significant system interaction.
- Sanitization: No sanitization or validation steps for content retrieved from external sources are defined in the skill instructions.
Audit Metadata