re-doc-malware
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and analysis of untrusted document content, creating a surface for indirect prompt injection attacks.
- Ingestion points: The agent is instructed to process and extract data from external files like PDFs, Word documents, and RTF samples using tools like pdf-parser and olevba (documented in
SKILL.md). - Boundary markers: The workflow lacks specific instructions for the agent to use delimiters or sanitization when interpreting the output of these tools.
- Capability inventory: The skill utilizes subprocess calls to execute multiple external analysis tools and perform file system operations for data archiving (documented in
SKILL.md). - Sanitization: No explicit content filtering or sanitization steps are defined for the extracted data before it enters the agent's context.
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of various forensic tools from official and well-known sources.
- Tools such as
oletoolsandxlmdeobfuscatorare fetched via standard package managers likepiporapt. - The skill references the
DidierStevens/DidierStevensSuiteGitHub repository, which is a standard resource in the security research community.
Audit Metadata