suggest-next-features

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands git log and jq to analyze the repository history and existing JSON configuration files. These operations are confined to local read-only context gathering.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from git logs and progress files to generate feature suggestions.
  • Ingestion points: git log output and claude-progress.txt from the local file system.
  • Boundary markers: Absent; instructions do not specify delimiters for external content.
  • Capability inventory: Subprocess calls for git and jq, and file-write access to feature_list.suggestions.json in SKILL.md.
  • Sanitization: Absent; the skill does not filter or sanitize the ingested project history before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 11:55 PM
Security Audit — agent-trust-hub — suggest-next-features