2slides-ppt-generator
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill demonstrates excellent security practices by implementing Server-Side Request Forgery (SSRF) protection in the
download_slides_pages_voices.pyscript. It ensures that download URLs are HTTPS and resolve to public IP addresses before pinning the connection to the verified IP.\n- [SAFE]: File operations are secured against path traversal attacks. Thesafe_user_pathfunction ensures that all file writes are restricted to the current workspace directory by resolving and validating paths against the current working directory.\n- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it ingests untrusted user content and document text for processing by a third-party AI service.\n - Ingestion points: User-provided strings in the
--contentparameter of generation scripts and document content processed during summarization workflows (SKILL.md, detailed-guide.md).\n - Boundary markers: Explicit delimiters for user content are not implemented in the API request payloads.\n
- Capability inventory: The skill has network access for API communication and file-write capabilities for saving presentation artifacts.\n
- Sanitization: The scripts perform regex validation on job identifiers and path-relative resolution for outputs to mitigate common exploitation vectors.
Audit Metadata