repo-pr-triage@1.0.0
VERIFIED· install onlyPublisher 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.
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 deviationsStatic findings
pr = self._make_pr(title="`rm -rf /`")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- 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.python3 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.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self.assertEqual(result["title"], "$(rm -rf /)")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.pr = self._make_pr(body="fix stuff; rm -rf /; echo pwned")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.python3 report.py <scores.json> [--output-dir <dir>]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.prompt = onboard.generate_interview_prompt("$(rm -rf /)/repo", ctx)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = scan.parse_repo("https://github.com/owner/repo; rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.pr = self._make_pr(title="$(rm -rf /)")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.self.assertIn("$(rm -rf /)", md)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = 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.result = 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.pr = _make_scored_pr(title="$(rm -rf /)")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = scan.parse_repo("https://github.com/owner/repo; rm -rf /")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ctx = {"metadata": {"name": "$(rm -rf /)", "description": "", "stargazerCount": 0,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.scan.load_vision("../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
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.