skills/gharib89/skills/super-agent/Gen Agent Trust Hub

super-agent

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes arbitrary shell commands defined in the fleet.json configuration file via bash -c. These commands are used for status notifications and checking provider quotas.
  • Evidence: scripts/notify.sh executes bash -c "$notify_cmd"; scripts/quota.sh executes bash -c "$cmd".
  • [DYNAMIC_EXECUTION]: The skill uses a pattern where the source code of internal scripts is pasted into agent messages to be executed on remote machines.
  • Evidence: reference/setup.md and reference/remote.md describe sending the full text of scripts/probe.sh and scripts/worktree.sh to remote T3 threads for execution via bash -s.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues and comments, which can influence its orchestration logic (e.g., routing, intake, and status reporting).
  • Ingestion points: GitHub API responses processed in scripts/intake.sh (issue labels/titles) and scripts/reconcile.sh (comment content/PR state).
  • Boundary markers: Technical delimiters are absent; the skill relies on instruction-level context management as described in SKILL.md.
  • Capability inventory: The skill possesses high-privilege capabilities including local and remote shell execution, GitHub API write access, and thread management.
  • Sanitization: Text data is structured using jq, which provides some character escaping, but the skill lacks specific sanitization for natural language instructions embedded in data.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 09:33 AM