NYC

project-session-management

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted data from SESSION.md and IMPLEMENTATION_PHASES.md to guide the agent's subsequent tasks and decision-making. 1. Ingestion points: SESSION.md, IMPLEMENTATION_PHASES.md. 2. Boundary markers: Markdown headers are used as structural delimiters. 3. Capability inventory: File system read/write, execution of local resume.sh script. 4. Sanitization: Absent; content is used directly for prompt interpolation.
  • Command Execution (SAFE): The included shell script (scripts/resume.sh) is a non-privileged, read-only diagnostic tool that uses common utilities like grep and sed to extract status information from the project's tracking file.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:58 PM