omh-tech-debt-audit

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and audits untrusted data from local repositories (source files, build manifests, and git history). This creates an attack surface where malicious instructions embedded in the analyzed code could attempt to influence the agent's behavior.
  • Ingestion points: The skill reads input from the repository root or a scoped path list, specifically manifests and source code files, as defined in SKILL.md.
  • Boundary markers: There are no explicit delimiters or specific 'ignore embedded instructions' markers defined to isolate the audited content from the agent's internal control logic.
  • Capability inventory: The skill maintains the ability to prepare and suggest shell commands (linters, audit tools, git churn analysis) for execution via the operator's terminal, as seen in references/debt-dimensions.md.
  • Sanitization: The skill instructions do not specify sanitization, escaping, or validation steps for content extracted from files during the audit process.
  • [COMMAND_EXECUTION]: The skill prepares and recommends terminal commands for analyzing technical debt. This includes git operations for churn ranking (git log --format= --name-only | sort | uniq -c | sort -rn | head -30) and various stack-specific linters. Safety rules in SKILL.md require that these commands remain as 'prepared context' until their exit status and output are observed through the user's terminal, providing a human-in-the-loop verification layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:34 PM
Security Audit — agent-trust-hub — omh-tech-debt-audit