sprint-compiler

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes content from multiple external files and interpolates them into its own output.
  • Ingestion points: The agent is instructed to read all files in the context/ directory and several specific markdown files (e.g., context-builder.md, jtbd-capture.md, dot-vote-*.md) from the working directory.
  • Boundary markers: There are no explicit boundary markers or instructions to treat the content of these files as untrusted data when generating the final report.
  • Capability inventory: The skill performs file read and write operations within the local working directory. It does not possess network access or the ability to execute system commands.
  • Sanitization: The instructions do not include any steps to sanitize, escape, or validate the content of the ingested files before they are processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:25 AM