Enterprise DNAEnterprise DNA

Skills

skill-security

by superagent-ai

A collection of security skills

Our verdict

Not reviewed yet

We have not reviewed skill-security yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About skill-security

skill-security is a collection of security-focused skills from superagent-ai, written in Python. It provides reusable components for integrating security capabilities into AI agent workflows, though specific skill details are not documented in the provided facts.

Best for

Developers building AI agents who need lightweight, open-source security utilities.

Use cases

  • Add security checks to agent pipelines
  • Reuse Python security utilities in agent projects
  • Extend agent behavior with security-related skills

Notes

80 stars on GitHub. Last updated 2026-08-15. Licensed MIT.

Pros

  • Part of a structured skills repository
  • Python-based, easy to integrate
  • Open source with public access

Cons

  • Limited documentation available
  • Small project with only 80 stars
  • Scope of security skills is unclear

Key facts

What we have checked

Days since the last commit
91
Checked GitHub
GitHub forks
13
Checked GitHub
GitHub stars
82
Checked GitHub
Installs
7.9K
Checked skills.sh
Open issues
0
Checked GitHub
Releases in the last 90 days
0
Checked GitHub

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

Stars and usage

How skill-security is growing

GitHub stars

80 to 82

stars. 1 Nov 2026 to 14 Nov 2026, 3 readings.

Source: GitHub. Checked .

Health and security

Is skill-security looked after, and what do its setup files show

Health score

66 out of 100

Does someone look after this repository? It does not say the code is good or safe. Worked out from GitHub signals checked . How it is worked out

PartPointsWhat we saw
Recent activity24.5 of 30Last push 91 days ago
Releases0 of 150 releases in 90 days
Issue repliesNot countedThe latest check has no issue response reading (fewer than 3 measured issues, or issues switched off)
Maintainer15 of 15Owned by an organisation
Official sourceNot countedMCP servers only

Security check static checks

61 out of 100

Reads what is published about the server: package advisories, licence, secrets in the documented setup and tool permissions. Nothing is installed or run, so this is not a security assessment. Checked by edna-skill-static-v1 main@0da315b873ed. What it checks

  • Medium Reads or points the agent at stored credentials (a credential file in the home directory): skills/skill-security/scripts/analyzers.py, line 157.
  • Medium Downloads code and runs it straight away: skills/skill-security/scripts/analyzers.py, line 161.
  • Medium Tells the agent to override the user or its own instructions (quoted, in a code block or described as an attack, possibly an example): skills/skill-security/SKILL.md, skills/skill-security/references/taxonomy.md, line 23, 2 places in all.
  • Low Reads or points the agent at stored credentials (a credential file in the home directory): skills/skill-security/references/taxonomy.md, line 93.
  • Low Collects the whole environment, which holds API keys and tokens: skills/skill-security/scripts/analyzers.py, line 155.
  • Low Tells the agent to skip permission or approval prompts: skills/skill-security/references/taxonomy.md, line 73.
  • Note No dependency list or install command was found in the skill, so there were no packages to look up on OSV.

Sources

Where this comes from

  • GitHubRegistry

    Checked · Days since the last commit, GitHub forks, GitHub stars, Open issues, Releases in the last 90 days

  • skills.shThird party

    Checked · Installs

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.