Skills
skills/bcanfield/agentic-tech-debt/debt-ops-metrics/Gen Agent Trust Hub

debt-ops-metrics

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a shell script using python3, git, and tail to calculate a deterministic repository hash and read the local metrics.jsonl file from the user's cache directory. These commands are used for local project identification and data retrieval.
  • [PROMPT_INJECTION]: The skill processes data from metrics.jsonl, a file which may be populated by external tools or hooks, creating an attack surface for indirect prompt injection. Ingestion points: metrics.jsonl (SKILL.md); Boundary markers: Absent; Capability inventory: python3, git, and tail execution (SKILL.md); Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 08:49 AM
Security Audit — agent-trust-hub — debt-ops-metrics