hermes-graphify-gsd-project-integration

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill automates the installation and upgrading of graphifyy (via pip) and get-shit-done-cc (via npx) from standard package registries (PyPI and NPM) to ensure the global toolchain is available for repository integration.
  • [COMMAND_EXECUTION]: Uses shell scripts to perform repository management tasks, including git operations, file system checks, and the execution of tool-specific commands like graphify update and gsd-sdk.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by ingesting and acting upon data from repository files such as AGENTS.md, README.md, and planning documents within the .planning/ directory. Evidence includes ingestion points in templates/ai-workflow.sh which reads state and roadmap files without explicit sanitization beyond standard JSON parsing.
  • [PERSISTENCE_MECHANISMS]: Provides infrastructure for autonomous continuation by referencing the installation of cron jobs, allowing the agent to resume tasks across multiple sessions. This is implemented via templates like templates/ai-workflow.sh calling external cron installation scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 12:23 PM
Security Audit — agent-trust-hub — hermes-graphify-gsd-project-integration