lov-thesis-polish
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external markdown files which creates a surface for indirect prompt injection. If a processed document contains malicious instructions, the agent might inadvertently execute them.
- Ingestion points: The skill reads user-provided thesis files in markdown format using a file reading tool as described in Step 1 of the workflow in
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the text of the thesis and the skill's operational instructions, nor are there warnings to ignore instructions found within the document.
- Capability inventory: The skill utilizes
ReadandWritecapabilities to access and create files on the local system (Step 5 inSKILL.md). - Sanitization: No input validation or content sanitization is performed on the ingested text before it is processed by the agent.
Audit Metadata