Skills/ClawHub/repo-pr-triage

repo-pr-triage@1.0.0

VERIFIED· install only

Publisher claims: "Triage GitHub PRs and issues using vision-based scoring. Use when a user wants to prioritize, score, review, de-duplicate, or batch-process open pull request..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher patrob · publishing for 278 daysInstalls 1,878Last detonated 30 min ago
$clawhub install repo-pr-triage
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: onboard.py: error: the following arguments are required: repo_url
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: report.py: error: the following arguments are required: scores_file
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: scan.py: error: the following arguments are required: repo_url, vision_path
0.2sprocess3 of 3 bundled scripts run with no arguments
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Destructive file system command detectedscripts/test_scan.py:325 · Destructive file system command detectedpr = self._make_pr(title="`rm -rf /`")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languagereferences/example-vision.md:165 · Authorization escalation language · informational: not an instruction file- Security mindset: bot has admin access, don't expose it to the worldFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionSKILL.md:20 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/report.py scores.json --output-dir ./triage-reportsFix: 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/scan.py:30 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedscripts/test_scan.py:322 · Destructive file system command detectedself.assertEqual(result["title"], "$(rm -rf /)")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedscripts/test_scan.py:330 · Destructive file system command detectedpr = self._make_pr(body="fix stuff; rm -rf /; echo pwned")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/report.py:6 · File type combined with upload action — agent may exfiltrate local data filespython3 report.py <scores.json> [--output-dir <dir>]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Destructive file system command detectedscripts/test_onboard.py:114 · Destructive file system command detectedprompt = onboard.generate_interview_prompt("$(rm -rf /)/repo", ctx)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicescripts/test_scan.py:34 · Destructive command against a filesystem root or deviceresult = scan.parse_repo("https://github.com/owner/repo; rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/onboard.py:24 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedscripts/test_scan.py:319 · Destructive file system command detectedpr = self._make_pr(title="$(rm -rf /)")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedscripts/test_report.py:88 · Destructive file system command detectedself.assertIn("$(rm -rf /)", md)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsscripts/test_scan.py:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesresult = scan.parse_repo("https://github.com/../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsscripts/test_onboard.py:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesresult = onboard.parse_repo("https://github.com/../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedscripts/test_report.py:86 · Destructive file system command detectedpr = _make_scored_pr(title="$(rm -rf /)")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedscripts/test_scan.py:34 · Destructive file system command detectedresult = scan.parse_repo("https://github.com/owner/repo; rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedscripts/test_onboard.py:112 · Destructive file system command detectedctx = {"metadata": {"name": "$(rm -rf /)", "description": "", "stargazerCount": 0,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathsscripts/test_scan.py:128 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesscan.load_vision("../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈1,058 tok
1 file · 10 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.