project-context

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill is designed to execute local system commands such as pwd, git status, and git log to identify project environments and verify their current state.\n- DATA_EXFILTRATION (LOW): The reference/projects-list.md file and SKILL.md contain hardcoded absolute filesystem paths (e.g., /Users/tmkipper/Desktop/tk_projects/) which expose the host's directory structure and user identity.\n- PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) as it ingests data from external project files and interpolates it into the agent context without sanitization.\n
  • Ingestion points: Reads content from <project-root>/.claude/PROJECT_CONTEXT.md, CLAUDE.md, and package.json.\n
  • Boundary markers: No delimiters or 'ignore instructions' warnings are used for the ingested content.\n
  • Capability inventory: The skill can execute local commands and write files.\n
  • Sanitization: No content validation or escaping is applied to the data read from external project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM