ieee-format-checker
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its document processing nature.
- Ingestion points: The skill reads .tex files via user-provided paths and processes pasted text or PDF content from the agent session (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or specific 'ignore instructions' warnings when handling the content of the papers being analyzed.
- Capability inventory: The agent context includes tools to read file system contents and an 'Edit tool' to perform modifications to local files (SKILL.md).
- Sanitization: There is no evidence of validation, sanitization, or filtering of document content before it is processed by the AI.
Audit Metadata