Report 01M7D7BAFK5D16F8QTB0PHHRD2 · checks-v2
deepworkplan-addon-devcontainer skill: automated checks
What HostedMCP checked on 14 Nov 2026, 14:28 UTC. Every result links to the public source it came from, so you can check it yourself.
7 of 7 checks ran · 1 high finding · not a security audit
- Checked
- 14 Nov 2026, 14:28 UTC
- Files read
- SKILL.md and scripts
- Methodology
- checks-v2
What to fix for a higher score
3 checks can earn more points. The next scan runs within a week, or right after the repository changes.
- No hidden instructions in SKILL.md up to +20 pts
Remove lines that tell the agent to ignore earlier instructions, switch off a safeguard or read credentials, and any hidden Unicode characters.
- Pre-approved tools are scoped up to +10 pts
Narrow
allowed-toolsto the commands the skill needs, for exampleBash(git status:*), notBashorBash(curl:*). The agent still asks before anything else. - SKILL.md follows the Agent Skills format up to +10 pts
Start SKILL.md with front matter holding a
name(lowercase letters, digits and hyphens, the same as the folder) and adescriptionunder 1,024 characters that says what the skill does and when to use it.
Origin
25 / 25 points- PassSource repository linked and reachable10 pts
dailybothq/deepworkplan-skill/skills/deepworkplan/addons/devcontainer is public and reachable
github.com/dailybothq/deepworkplan-skill/tree/HEAD/skills/deepworkplan ↗ - Pass
- PassCommit or release in the last year5 pts
Last commit 2026-10-28
github.com/dailybothq/deepworkplan-skill/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
0 / 30 points- FindingNo hidden instructions in SKILL.md20 pts
Tells the agent to read credentials on line 151
github.com/dailybothq/deepworkplan-skill/blob/HEAD/skills/deepworkplan ↗How to fix: Remove lines that tell the agent to ignore earlier instructions, switch off a safeguard or read credentials, and any hidden Unicode characters.
- FindingPre-approved tools are scoped10 pts
Bash lets the agent run any shell command without asking
github.com/dailybothq/deepworkplan-skill/blob/HEAD/skills/deepworkplan ↗How to fix: Narrow
allowed-toolsto the commands the skill needs, for exampleBash(git status:*), notBashorBash(curl:*). The agent still asks before anything else.
Format
5 / 15 points- PartialSKILL.md follows the Agent Skills format5 / 15 pts
the description does not say when to use the skill; name "deepworkplan-addon-devcontainer" differs from the folder "devcontainer"
github.com/dailybothq/deepworkplan-skill/blob/HEAD/skills/deepworkplan ↗How to fix: Start SKILL.md with front matter holding a
name(lowercase letters, digits and hyphens, the same as the folder) and adescriptionunder 1,024 characters that says what the skill does and when to use it.
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.