Caveat verdict
agent-mail-guard
Email sanitization middleware that explicitly detects and blocks prompt injection, base64 payloads, homoglyphs, and markdown exfiltration; a defensive security tool with no malicious behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (10)
Pipe to python — executes piped content as Python code
README.md · code · | python3
Prompt injection — tries to override agent instructions
README.md · code · Ignore previous instructions
Unicode homoglyph detected — uses lookalike characters to evade pattern matching
test_sanitizer.py · prose
Possible prompt injection — attempts to redefine agent identity
README.md · code · You are now
subprocess execution — runs system commands from Python
README.md · code · subprocess.run(
Raw model control tokens — prompt injection via token manipulation
sanitize_core.py · prose · downgraded · [INST]
Prompt injection — disregard instructions variant
test_sanitizer.py · prose · downgraded · Disregard all previous instructions
<script> tag in markdown — potential code injection
test_sanitizer.py · prose · downgraded · <script>
Instructs covert action — may act without user awareness
README.md · prose · downgraded · silently
Fake system prompt — attempts to inject instructions
test_cal_sanitizer.py · prose · downgraded · system: You are
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
Is this flag fair?
Thanks — recorded.