academic-norm-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external academic manuscript text provided by users, which introduces a potential surface for instructions embedded in that data to influence agent behavior.
- Ingestion points: The manuscript text provided for citation and abbreviation review as defined in the 'Required Inputs' section of
SKILL.md. - Boundary markers: The instructions do not define specific delimiters (such as XML tags or dedicated markdown blocks) to clearly separate the untrusted manuscript text from the skill's operational instructions.
- Capability inventory: The skill does not possess any tools for network communication, file system modifications, or shell command execution, which limits the potential impact of any injection attempt.
- Sanitization: There are no instructions or mechanisms described for sanitizing, escaping, or validating the manuscript content before it is processed by the agent.
Audit Metadata