DC extracting-browser-history-artifacts
Extracts and analyzes browser history, cookies, cache, downloads, and bookmarks from Chrome, Firefox, and Edge using sqlite3, DB Browser for SQLite, Hindsight, and NirSoft tools (BrowsingHistoryView, ChromeCacheView, MZCacheView). Use when performing digital forensics or incident response on a disk image or live system and you need timeline evidence of a user's web activity.
Extracts and analyzes browser history, cookies, cache, downloads, and bookmarks from Chrome, Firefox, and Edge using sqlite3, DB Browser for SQLite…
As a process C 62/100 · Has gaps — weak spots: when it triggers, failures and branches, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 10
-
high Exfiltration
intent-browser-credential-storescripts/agent.py:165Accesses a browser credential / cookie storecookies = extract_chrome_cookies(os.path.join(chrome_dir, "Cookies"))
Medium and low: 9
-
medium Exfiltration
intent-browser-credential-storescripts/agent.py:86Accesses a browser credential / cookie store (quoted — discussed, not commanded)"""Extract cookies from Chrome Cookies database."""
quoted -
medium Exfiltration
intent-browser-credential-storescripts/agent.py:128Accesses a browser credential / cookie store (quoted — discussed, not commanded)"""Extract cookies from Firefox cookies.sqlite."""
quoted -
medium Exfiltration
intent-browser-credential-storescripts/agent.py:175Accesses a browser credential / cookie store (quoted — discussed, not commanded)cookies = extract_firefox_cookies(os.path.join(firefox_dir, "cookies.sqlite"))
quoted -
medium Exfiltration
intent-browser-credential-storeSKILL.md:65Accesses a browser credential / cookie store (documentation of a security skill)# Key files: places.sqlite, cookies.sqlite, formhistory.sqlite, logins.json,
security skill -
medium Exfiltration
intent-browser-credential-storeSKILL.md:66Accesses a browser credential / cookie store (documentation of a security skill)# key4.db, sess…lz4, webappsstore.sqlite
security skill -
medium Exfiltration
intent-browser-credential-storeSKILL.md:75Accesses a browser credential / cookie store (documentation of a security skill)cp -r $FIREFOX_WIN/{places.sqlite,cookies.sqlite,formhistory.sqlite,logins.json} \security skill -
medium Exfiltration
intent-browser-credential-storeSKILL.md:199Accesses a browser credential / cookie store (documentation of a security skill)sqlite3 /cases/case…001/browser/chrome/Cookies << 'SQL'
security skill
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 62/100
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2743 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 377: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 11 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.