Skills
skills/dev-goraebap/agent-collabo/agent-collabo-updater/Gen Agent Trust Hub

agent-collabo-updater

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches a version manifest (manifest.json) from the author's official GitHub repository to identify available updates and deprecated skills.
  • [COMMAND_EXECUTION]: Utilizes the bash tool to execute npx skills add and npx skills remove commands. These commands are generated dynamically based on the content of the remote manifest to manage local skill files.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted data from an external manifest to construct and execute shell commands.
  • Ingestion points: Remote manifest.json file from https://raw.githubusercontent.com/dev-goraebap/agent-collabo/main/manifest.json.
  • Boundary markers: None identified; the skill parses the JSON directly and interpolates keys/values into commands.
  • Capability inventory: Full shell execution capability via the bash tool to run package management commands (SKILL.md Step 5).
  • Sanitization: The workflow does not specify any sanitization, escaping, or validation logic for the skill names or version strings retrieved from the manifest before they are used in shell command interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 02:57 PM
Security Audit — agent-trust-hub — agent-collabo-updater