farhoodlabs/trebuchet
8
0
Fork 0
Code Issues Pull Requests 5 Actions Packages Projects Releases Wiki Activity

docs: simplify prompt injection disclaimer in README

Browse Source
This commit is contained in:
ajmallesh
2026-03-07 11:48:59 -08:00
parent 023cc953db
commit 58afb767c6
1 changed files with 2 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -5
View File
@@ -677,12 +677,9 @@ Shannon is designed for legitimate security auditing purposes only.
Windows Defender may flag files in `xben-benchmark-results/` or `deliverables/` as malware. These are false positives caused by exploit code in the reports. Add an exclusion for the Shannon directory in Windows Defender, or use Docker/WSL2.
#### **7. Prompt Injection Risk from Untrusted Repositories**
#### **7. Security Considerations**
Shannon feeds repository source code into LLM prompts for white-box analysis. A malicious repository can embed adversarial instructions in comments, strings, or documentation that hijack agent behavior.
> [!WARNING]
> **Do not scan repositories from untrusted sources.** Only scan repositories you own, trust, or have reviewed for adversarial content.
Shannon Lite is designed for scanning repositories and applications you own or have explicit permission to test. Do not point it at untrusted or adversarial codebases. Like any AI-powered tool that reads source code, Shannon Lite is susceptible to prompt injection from content in the scanned repository.
## 📜 License