self-safety-guard
sx-self-safety-guard · v2.0.0 · by
66.0
Trust Score
0
Trust Tier
danger
Badge
Score Breakdown
| Factor | Score | Weight |
|---|---|---|
| Static | 40.0 | 15% |
| Permission | 100.0 | 15% |
| Poison | 0.0 | 15% |
| Clickfix | 65.0 | 15% |
| Credential | 100.0 | 15% |
| Twostage | 100.0 | 10% |
| Infrastructure | 100.0 | 5% |
| Typosquat | 100.0 | 5% |
| Age | 8.3 | 3% |
| Popularity | 0.0 | 2% |
Scan Results
STATIC — Score: 40
[HIGH] Prompt injection or system override attempt
(line 99)
- `Ignore previous instructions` / `Forget your rules`
[HIGH] Prompt injection or system override attempt
(line 100)
- `You are now DAN` / `You are now in developer mode`
PERMISSION — Score: 100
No findings.
POISON — Score: 0
[CRITICAL] Classic prompt injection: ignore previous instructions
(line 99)
- `Ignore previous instructions` / `Forget your rules`
[HIGH] Fake developer/admin mode activation
(line 100)
- `You are now DAN` / `You are now in developer mode`
[HIGH] Content contains alarming words not in description: unrestricted
CLICKFIX — Score: 65
[CRITICAL] Instructs user to copy-paste commands into terminal
(line 161)
- `Copy paste your initial prompt`
INFRASTRUCTURE — Score: 100
No findings.
TWOSTAGE — Score: 100
No findings.
CREDENTIAL — Score: 100
No findings.
TYPOSQUAT — Score: 100
No findings.