paper-draft-consistency-editor
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and process untrusted text from external files while having access to high-privilege tools.
- Ingestion points: The agent reads LaTeX and Markdown source files (e.g.,
main.tex,sections/*.tex) as specified in Step 1 ofSKILL.md. - Boundary markers: There are no instructions to wrap external content in delimiters or explicit warnings to ignore embedded instructions within the paper drafts.
- Capability inventory: The skill's configuration allows the use of
Bash,Write, andEdittools, which could be abused if the agent inadvertently follows malicious instructions hidden in the text it edits. - Sanitization: The skill lacks sanitization or validation logic for the content read from paper source files before it is processed by the agent.
Audit Metadata