Skills/ClawHub/hum-writer

hum-writer@0.2.1

CAUTION· static only

Publisher claims: "AI content writer that researches, outlines, drafts, publishes, and manages engagement for LinkedIn and X using your voice and style guidelines." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher jyek · publishing for 222 daysInstalls 864Last detonated 7 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Python subprocess execution detectedscripts/lib/bird_x.py:106 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedscripts/lib/vendor/bird-search/lib/twitter-client-utils.js:174 · Destructive file system command detected// Handle LINK entities by appending URL in markdown formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/bird_x.py:65 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/feed/source/youtube.py:85 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=True, timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/feed/ranker.py:7 · File type combined with upload action — agent may exfiltrate local data filespython3 ranker.py --input /tmp/feed_posts.json --output /tmp/feed_ranked.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/lib/bird_x.py:155 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/lib/image-gen/generate.py:269 · File type combined with upload action — agent may exfiltrate local data filesif result and not args.json and not args.output:Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/loop.py:60 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandscripts/act/connectors/linkedin.py:57 · File permission modification command — agent changes file ownership/permissionsprint(f"Warning: credential file {cred_path} is readable by group/others. Run: chmod 600 {cred_path}", file=sys.stderr)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionscripts/feed/source/youtube.py:228 · File type combined with upload action — agent may exfiltrate local data filesparser.add_argument("--output", default=str(_CFG["feed_raw"] / "youtube_feed.json"), help="Output JSON path")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/lib/youtube_yt.py:105 · Python subprocess execution detectedproc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/feed/ranker.py:9 · File type combined with upload action — agent may exfiltrate local data filesReads preferences.json and applies author/topic/keyword weights to each post.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/feed/digest.py:6 · File type combined with upload action — agent may exfiltrate local data filespython3 digest.py --input /tmp/feed_posts.json [--youtube-input /tmp/youtube_feed.json] [--max-posts 10]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandscripts/act/connectors/x.py:57 · File permission modification command — agent changes file ownership/permissionsprint(f"Warning: credential file {cred_path} is readable by group/others. Run: chmod 600 {cred_path}", file=sys.stderr)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈2,091 tok
1 file · 73 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jyek: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jyekPropose a patch to the maintainer