slides-extract

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behaviors, obfuscation, or unauthorized network operations were detected. The skill performs legitimate template analysis consistent with its documentation.
  • [COMMAND_EXECUTION]: The skill uses local shell commands (mkdir) and the uvx package runner to execute the agent-slides utility. These operations are necessary for creating the output environment and running the template extraction logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection through data ingestion.
  • Ingestion points: The skill processes external .pptx files provided by the user in Step 2.
  • Boundary markers: None explicitly defined in the prompt instructions.
  • Capability inventory: The skill can create local directories, write multiple JSON artifacts, and execute the agent-slides CLI tool.
  • Sanitization: Data is parsed into structured JSON schemas (contracts) such as template_layout.json and resolved_manifest.json, which significantly reduces the risk of the agent interpreting slide content as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:42 AM
Security Audit — agent-trust-hub — slides-extract