Skills
skills/sethdford/claude-skills/branching-strategy/Gen Agent Trust Hub

branching-strategy

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates user-supplied input via the $ARGUMENTS variable in the SKILL.md file context section without providing clear boundary markers.
  • Ingestion points: User input is directly interpolated into the senior tech lead persona context in SKILL.md.
  • Boundary markers: There are no delimiters (e.g., XML tags, triple backticks) or specific instructions to the agent to ignore or sanitize embedded commands within the $ARGUMENTS field.
  • Capability inventory: The skill possesses no executable capabilities, tool access, or file system permissions, significantly limiting the impact of any potential injection.
  • Sanitization: No input validation or escaping mechanisms are implemented for the provided arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 10:22 AM