skills/open-gsd/gsd-core/gsd-update/Gen Agent Trust Hub

gsd-update

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute local workflow markdown files located in ~/.claude/gsd-core/workflows/. These workflows orchestrate version detection, user confirmation, and the update process.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the npm registry to check for new versions and download updates. This interaction with a well-known service is standard for the skill's intended purpose of software maintenance.
  • [PROMPT_INJECTION]: The skill handles untrusted data through the ingestion of external changelogs and user-provided $ARGUMENTS.
  • Ingestion points: User-supplied arguments and remote changelog content fetched during the update process.
  • Boundary markers: None explicitly defined in the SKILL.md file.
  • Capability inventory: The skill has access to Bash, Read, Write, and Edit tools.
  • Sanitization: No specific sanitization or filtering logic for the ingested content is described in the top-level instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:38 PM
Security Audit — agent-trust-hub — gsd-update