project-manager-senior

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and act upon data from external project specification files.
  • Ingestion points: The agent reads requirements from ai/memory-bank/site-setup.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the specification files.
  • Capability inventory: The agent can write files to ai/memory-bank/tasks/ and generate shell commands for developer execution.
  • Sanitization: The skill lacks mechanisms to sanitize or validate the content of the project specifications before processing.
  • [COMMAND_EXECUTION]: The skill instructions require the agent to generate and include a specific shell command in its output for quality assurance tasks.
  • Evidence: The skill specifies the use of ./qa-playwright-capture.sh http://localhost:8000 public/qa-screenshots within the Quality Requirements section.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:44 AM
Security Audit — agent-trust-hub — project-manager-senior