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 logandjqto 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 logoutput andclaude-progress.txtfrom the local file system. - Boundary markers: Absent; instructions do not specify delimiters for external content.
- Capability inventory: Subprocess calls for
gitandjq, and file-write access tofeature_list.suggestions.jsonin SKILL.md. - Sanitization: Absent; the skill does not filter or sanitize the ingested project history before processing.
Audit Metadata