skills/seabbs/skills/pr/Gen Agent Trust Hub

pr

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs direct shell command interpolation using the user-provided $ARGUMENTS variable (intended to be an issue number). Commands like git checkout -b issue-$ARGUMENTS-[desc] and gh issue view #$ARGUMENTS could be exploited if the input contains shell metacharacters (e.g., semicolons or backticks), leading to arbitrary code execution on the user's machine.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by processing untrusted data from GitHub issues.
  • Ingestion points: Untrusted content is ingested from the output of gh issue view into the context of 'Haiku' and 'Sonnet' agents.
  • Boundary markers: There are no explicit boundary markers or instructions to the sub-agents to ignore embedded commands within the issue text.
  • Capability inventory: The agent has the capability to write files (issue_analysis_$ARGUMENTS.md), execute shell commands (git, gh, lint, tests), and modify the codebase.
  • Sanitization: No sanitization or filtering of the issue description is performed before it is analyzed and used to generate implementation plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:58 AM