mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(security): catch multi-word prompt injection in skills_guard

Browse source 
The regex `ignore\s+(previous|all|...)\s+instructions` only matched
a single keyword between 'ignore' and 'instructions'. Phrases like
'ignore all prior instructions' bypassed the scanner entirely.

Changed to `ignore\s+(?:\w+\s+)*(previous|all|...)\s+instructions`
to allow arbitrary words before the keyword.
This commit is contained in:
0xbyt4 2026-02-28 20:15:25 +03:00
parent 6366177118
commit 4ea29978fc
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tools/skills_guard.py
View file

@ -157,7 +157,7 @@ THREAT_PATTERNS = [
"markdown link with variable interpolation"),
# ── Prompt injection ──
(r'ignore\s+(previous|all|above|prior)\s+instructions',
(r'ignore\s+(?:\w+\s+)*(previous|all|above|prior)\s+instructions',
"prompt_injection_ignore", "critical", "injection",
"prompt injection: ignore previous instructions"),
(r'you\s+are\s+now\s+',