Skills
Navigate
skills/mukul975/anthropic-cybersecurity-skills/extracting-browser-history-artifacts/Gen Agent Trust Hub

extracting-browser-history-artifacts

Warn

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill accesses browser artifact files containing session cookies and stored credentials, specifically Cookies, Login Data, and logins.json.
  • [EXTERNAL_DOWNLOADS]: The workflow requires installing the pyhindsight forensic tool from a public repository without version constraints.
  • [COMMAND_EXECUTION]: The instructions involve running several shell commands for file operations and database querying, including mount, cp, sha256sum, and sqlite3.
  • [PRIVILEGE_ESCALATION]: The skill uses the mount command to attach forensic images, which typically requires root or administrative privileges.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted browser data, creating a potential vector for indirect prompt injection. * Ingestion points: Browser database files read by scripts/agent.py and sqlite3 commands in SKILL.md. * Boundary markers: None identified. * Capability inventory: File system read/write, shell command execution, and database manipulation. * Sanitization: Python script uses parameterized queries for SQLite interactions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 15, 2026, 06:02 AM