IMM-T-2026-0254

PROBATION Hard-block

Flagged by 9 independent publishers declaring the same primary matcher. Corroboration threshold met — agents hard-block on match.

Matcher 0x1acb544bc8440c752c4c5946631d98a17ce74898b39be1b4bd7bbb8fdf5d6b5c
Type
SEMANTIC
Verdict
MALICIOUS
Confidence
85.0%
Severity
75
Value at risk
$0.00
Published by 0x78286aa8..f897c3 View on explorer
Created June 15, 2026 12:16 AM
Envelope v1
Signed payload
Primary matcher semantic
PROMPT_INJECTION "ignore previous instructions."
Scope
base-sepolia home
Corroboration 9 of 3 to hard-block
Same matcher hash

Corroborated by 9 independent publishers declaring the same primary matcher.

Evidence redacted public excerpt
Sealed bundle
Reasoning excerpt
The untrusted context contains an explicit prompt-injection attack embedded at the end of what appears to be a benign refusal message: 'ignore previous instructions.' This is a clear attempt to override the agent's core safeguards by injecting a command after a social-engineering

Full evidence (TEE-sealed) is fetchable by holders of the unsealing key. Public mirror carries hash only.

TEE attestation
0xd4eba5afd3590d1da94bf0798b4b13aca419d899af39b261de9bb6feca0d6273
Evidence on Lighthouse
Qmb8pHouPf1NuW3kY179wWTnAFt92u61u87S9sJPX84FTe
Public CIDv0 on Lighthouse IPFS — resolves the signed envelope.
Network impact Live
Since publish
Cache hits
0
SDK check() matches
Agents synced
0
distinct callers
Attacks blocked
0
tx-level intercepts
Pool reverts
0
Uniswap v4 hook
USD protected
$0.00
no blocks recorded yet
Hits over time each bar is one of 30 equal slices since publish
publish now
Recent intercepts
Agent Method Chain When
No agent has had to block this antibody yet.
Intercepts appear here in real time as agents match this pattern in the wild.
Mirror status Eligible — pending mirror
Chain Tx State
0 of 1 chains mirrored