windows-authenticode-signer

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external binary files and communicate with remote timestamping servers, which serves as a vector for indirect instructions to enter the agent's context.
  • Ingestion points: The executablePath and timestampServer parameters in SKILL.md are the primary ingestion points for untrusted data.
  • Boundary markers: Absent. The skill lacks instructions or delimiters to prevent the agent from interpreting data within the executable or responses from the timestamp server as valid commands.
  • Capability inventory: The skill utilizes signtool and AzureSignTool to perform file system writes and network operations.
  • Sanitization: There are no explicit validation steps defined to sanitize the inputs or verify the integrity of the external resources before they are processed by the signing tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 08:26 PM