analyzing-browser-forensics-with-hindsight
Analyze Chromium-based browser artifacts using Hindsight to extract browsing history, downloads, cookies, cached content, autofill data, saved passwords, and browser extensions from Chrome, Edge, Brave, and Opera for forensic investigation.
51
56%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/analyzing-browser-forensics-with-hindsight/SKILL.mdSecurity
2 findings — 1 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Suspicious download URL detected (high risk: 0.80). Several entries are high-risk indicators—most notably a direct .exe on a suspicious domain (https://cdn.evil-updates.com/client.exe) plus multiple personal/file‑sharing links (MEGA, transfer.sh, Google Drive, Pastebin) and a phishing-looking domain (phish-domain.com) which are common malware distribution vectors despite other benign URLs in the list.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests outsider-authored free text from the user’s browser profile databases—e.g., `History`/`urls.title` and `downloads.tab_url`/`downloads.target_path`—which are populated from arbitrary web content and thus can contain attacker-controlled strings that get serialized into JSON/printed output and then can be fed into the agent/LLM context.
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- Commit
0445030
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.