agent-owasp-compliance

github.com/github/awesome-copilot
Verdict: Generally safe
0 critical0 high3 medium
B
SCORE 75 / 100
$skillox install agent-owasp-complianceSoon
Sign in to followFollowing emails you when a re-scan drops the grade. Opt-out is per-creator on /account/billing.

Why grade B?

score · 75 / 100

The current grade reflects 3 medium findings (3+ MEDs → B).

0 CRIT0 HIGH3 MED0 LOW
To reach a higher grade
  • A
    Reach Atarget score 95

    Resolve 1 of 3 MED (cap is 2).

Thresholds are documented at /docs/grading. Source-of-truth is the grade() function in @skillox/scanner.

Latest scan findings

Scan crawl-qdc7eiq2r0cm6p1wycdlnbjd · Thu, 28 May 2026 17:20:42 GMT · 2ms

med
Arbitrary subprocess execution detected
The skill spawns subprocesses. Without a capability manifest declaring this, the skill could execute arbitrary commands.
rule: subprocess-executionline: 125CWE-78
▾
123- Tool registration with explicit allowlists (not open-ended)
124- Argument validation before tool execution
125- No `subprocess.run(shell=True)` with user-controlled input← spawns a subprocess outside declared capabilities
126- No `eval()` or `exec()` on agent-generated code without sandbox
127
med
Arbitrary subprocess execution detected
The skill spawns subprocesses. Without a capability manifest declaring this, the skill could execute arbitrary commands.
rule: subprocess-executionline: 126CWE-78
▾
124- Argument validation before tool execution
125- No `subprocess.run(shell=True)` with user-controlled input
126- No `eval()` or `exec()` on agent-generated code without sandbox← spawns a subprocess outside declared capabilities
127
128**Passing example:**
med
No capability manifest declared
The skill ships without a `manifest.yaml` or `capabilities` block in its frontmatter. Without a manifest, the runtime cannot enforce what this skill is permitted to do.
rule: no-manifest
▾
View latest scan →
skillox.io/c/agent-owasp-compliance