cracked-profile

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands such as echo, date +%F, git config user.name, and gh api user to resolve data paths, get the current date, and infer user profile information (name and GitHub handle).
  • [DATA_EXFILTRATION]: The agent is directed to scan personal user directories (~/Downloads, ~/Documents, ~/Desktop) for files matching *resume* or *cv*. While this is a functional requirement for creating a career profile, it involves accessing sensitive personal folders. The skill mitigates risk by instructing the agent to confirm the file path with the user rather than assuming it.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads content from user-provided resumes and local Markdown files (profile.md, journal.md) to populate the agent's context.
  • Ingestion points: Reads profile.md, journal.md, and external resume files (PDF, Docx, MD, Tex).
  • Boundary markers: No specific delimiters or "ignore embedded instructions" headers are defined for the file content.
  • Capability inventory: The agent can execute shell commands (git, gh, date) and perform file read/write operations.
  • Sanitization: No specific sanitization or validation of the ingested file content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 06:30 AM