Skip to content

Add SafeSkill security badge (86/100 — Passes with Notes)#6

Open
OyaAIProd wants to merge 1 commit into
callibrity:mainfrom
OyaAIProd:safeskill-scan-1776564425646
Open

Add SafeSkill security badge (86/100 — Passes with Notes)#6
OyaAIProd wants to merge 1 commit into
callibrity:mainfrom
OyaAIProd:safeskill-scan-1776564425646

Conversation

@OyaAIProd
Copy link
Copy Markdown

⚠️ SafeSkill Security Scan Results

Metric Value
Overall Score 86/100 (Passes with Notes)
Code Score 100/100
Content Score 61/100
Findings 48 findings detected (6 high)
Taint Flows 0
Files Scanned 0
Scan Duration 0.5s

Top Findings

  • 🟠 high: Context boundary escape detected (fake-xml-boundary): "" (specs/done/058-conformance-elicitation-sampling-tools.md:16)
  • 🟠 high: Context boundary escape detected (fake-xml-boundary): "" (specs/done/085-mocapi-model-module.md:72)
  • 🟠 high: Detected instruction-override attempt: "Replace the prompt" (specs/done/087-migrate-prompts-to-model.md:5)
  • 🟠 high: Context boundary escape detected (fake-xml-boundary): "" (specs/done/087-migrate-prompts-to-model.md:38)
  • 🟠 high: Context boundary escape detected (fake-xml-boundary): "" (specs/done/094-tool-execution-errors-as-is-error-result.md:21)

View full report on SafeSkill


About SafeSkill

SafeSkill is a free, open-source security scanner for AI tools, MCP servers, and Claude Code skills. We scan for code exploits, prompt injection, and data exfiltration risks.

False positive? We take accuracy seriously. If any finding above is incorrect, please open an issue and we will fix it immediately.

Signed-off-by: SafeSkill Scanner <mk@oya.ai>
@jwcarman
Copy link
Copy Markdown
Contributor

jwcarman commented May 7, 2026

The findings look to all be in markdown files? Is that right?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants