tdd-plan

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a read-only directory listing command (ls -t docs/cycles/*.md) to locate the most recent cycle documentation. This is a standard and safe operational procedure.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes platform-native WebSearch and WebFetch capabilities to verify library versions and documentation during implementation planning.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. Ingestion points: Data from WebSearch and WebFetch tools (SKILL.md). Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands in the external data. Capability inventory: Execution of shell commands (ls) and invocation of the tdd-core:plan-review skill. Sanitization: Absent; the skill does not specify any filtering or validation for retrieved external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:21 AM
Security Audit — agent-trust-hub — tdd-plan