growth-audit

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading and interpreting untrusted third-party codebases and documentation.
  • Ingestion points: Reads the entire project codebase including README.md, package manifests, landing pages, and source files via file read operations.
  • Boundary markers: Lacks delimiters or instructions to treat ingested content as data, increasing the risk that the agent may follow instructions embedded within the audited files.
  • Capability inventory: The skill performs extensive file system read operations and appends execution logs to a file in the user's home directory (~/.claude/projects/skill-telemetry.md).
  • Sanitization: No sanitization or validation logic is defined for the ingested codebase content.
  • [SAFE]: The skill uses project-local metadata and standard configuration files (e.g., package.json, Info.plist) to determine the product's tech stack and growth context.
  • [SAFE]: The execution telemetry feature writes to a specific logging file, which is a common practice for internal performance monitoring in the targeted environment, though it occurs outside the project root.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:57 AM
Security Audit — agent-trust-hub — growth-audit