Report 01M7EWJG1QSAEQCX5YW6P7A3W8 · checks-v2
patching-bugs skill: automated checks
What HostedMCP checked on 15 Nov 2026, 05:58 UTC. Every result links to the public source it came from, so you can check it yourself.
7 of 7 checks ran · 0 high findings · not a security audit
- Checked
- 15 Nov 2026, 05:58 UTC
- Files read
- SKILL.md and scripts
- Methodology
- checks-v2
What to fix for a higher score
One check can earn more points. The next scan runs within a week, or right after the repository changes.
- Open source license (OSI) up to +10 pts
Add a LICENSE file and name it by its SPDX id in the SKILL.md front matter, for example
license: MIT.
Origin
15 / 25 points- PassSource repository linked and reachable10 pts
trailofbits/skills/plugins/patching-bugs/skills/patching-bugs is public and reachable
github.com/trailofbits/skills/tree/HEAD/plugins/patching-bugs/skills/p ↗ - FindingOpen source license (OSI)10 pts
CC-BY-SA-4.0 is not OSI-approved
spdx.org/licenses/CC-BY-SA-4.0.html ↗How to fix: Add a LICENSE file and name it by its SPDX id in the SKILL.md front matter, for example
license: MIT. - PassCommit or release in the last year5 pts
Last commit 2026-11-11
github.com/trailofbits/skills/commits ↗
Scripts
30 / 30 points- PassNo download-and-run or credential theft in scripts30 pts
No scripts in the skill folder
Instructions to the agent
30 / 30 points- PassNo hidden instructions in SKILL.md20 pts
No override phrases, safeguard switches, credential requests or hidden characters
github.com/trailofbits/skills/blob/HEAD/plugins/patching-bugs/skills/p ↗ - PassPre-approved tools are scoped10 pts
No pre-approved tools; the agent asks before using one
github.com/trailofbits/skills/blob/HEAD/plugins/patching-bugs/skills/p ↗
Format
15 / 15 points- PassSKILL.md follows the Agent Skills format15 pts
Valid name and description; says when to use it; 153 lines
github.com/trailofbits/skills/blob/HEAD/plugins/patching-bugs/skills/p ↗
What these checks do not cover
- Scripts are read, never run. Their logic is not audited, and up to five scripts per skill are read.
- Results describe the skill folder on the date above; a later commit can differ.
- A pass is not a guarantee of safety. Read the scripts before you let an agent run them, and keep allowed-tools narrow.