eshaansaini2004/Prompt Injection Scanner
Scan PR descriptions, issue bodies, or any text for prompt injection attacks using PIF.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Activelast commit May 14, 2026
- License
- None
Pinned Snippet
uses: eshaansaini2004/prompt-injection-firewall@5576e57bbca8f1c45974180de1868e245832959e # no releases — HEAD as of 2026-07-11tags can be moved; commit SHAs can't. why a SHA?
Inputs
| name | description | required | default |
|---|---|---|---|
| text | Text to scan for prompt injection attacks. | yes | — |
| threshold | Confidence threshold to flag as injection (0.0–1.0). Default is 0.75. | no | 0.75 |
| fail_on_injection | Fail the workflow step if an injection is detected. Default true. | no | true |
| github_token | GitHub token for posting comments. Pass secrets.GITHUB_TOKEN. | no | "" |
Outputs
| name | description |
|---|---|
| is_injection | true if injection detected, false otherwise |
| confidence | Detection confidence score (0.0–1.0) |
| attack_type | Detected attack category |