dev2-design

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes data from external files (tmp_context.md and tmp_exploration.md) which may contain untrusted content from the user's codebase.
  • Ingestion points: Files located at .llm/$ARGUMENTS/tmp_context.md and .llm/$ARGUMENTS/tmp_exploration.md.
  • Boundary markers: The skill does not use delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The skill has the ability to read and write files within the .llm directory and invoke subsequent workflow steps (/dev3-prd).
  • Sanitization: No sanitization or filtering is performed on the ingested content before it is processed by the agent.
  • [PROMPT_INJECTION]: The skill uses user-supplied input ($ARGUMENTS) directly to construct file system paths (e.g., .llm/$ARGUMENTS/design.md). This lacks validation and could potentially be exploited via directory traversal sequences (e.g., ../) to influence file access or creation outside the intended directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:37 AM
Security Audit — agent-trust-hub — dev2-design