progress-run

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to read and act upon external files such as PLAN.md or TODO.md as authoritative instructions. This creates a surface for indirect prompt injection where malicious instructions embedded in a project's documentation could influence agent behavior.
  • Ingestion points: The agent is instructed to read plan files, handoff files, or .pi files from the repository.
  • Boundary markers: There are no explicit instructions to use delimiters or to disregard instructions contained within the ingested data.
  • Capability inventory: The workflow allows the agent to inspect git status, read file contents, execute code slices, and modify files.
  • Sanitization: No sanitization or validation of the input file content is performed before the agent treats it as authoritative.
  • [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata. It does not include any standalone scripts, binaries, or third-party dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 11:32 AM
Security Audit — agent-trust-hub — progress-run