argument-audit
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted external data (academic papers) and possesses tools capable of network and file operations.
- Ingestion points: The agent is instructed to read and extract arguments from external papers provided by the user (referenced in SKILL.md).
- Boundary markers: The instructions do not define delimiters or specific markers to isolate the untrusted paper content from the agent's instructions.
- Capability inventory: The skill utilizes network tools (WebSearch, WebFetch) and file system tools (Read, Grep, Glob).
- Sanitization: No sanitization or validation of the ingested paper content is defined to prevent embedded instructions from influencing the agent's behavior.
Audit Metadata