Skip to content

Feature: HarmActEval benchmark for agent tool calls #206

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
prane-eth wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Feature: HarmActEval benchmark for agent tool calls #206

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3bbf04c
Added HarmActEval benchmark for agent tool calls
prane-eth Mar 18, 2026
fec2621
Renamed Safe@k to SafeActions@k
prane-eth Mar 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,6 +99,7 @@ DeepTeam runs **locally on your machine** and uses LLMs for both attack simulati
- Graphic Content — violence, sexual content
- Personal Safety — self-harm, dangerous advice
- Unexpected Code Execution — arbitrary code generation
- HarmActEval — agentic evaluation of harmful actions

</details>

Expand Down
2 changes: 2 additions & 0 deletions deepteam/frameworks/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
from .mitre.mitre import MITRE
from .beavertails.beavertails import BeaverTails
from .owasp_top_10_agentic.owasp_top_10_agentic import OWASP_ASI_2026
from .harmacteval.harmacteval import HarmActEval

__all__ = [
"AISafetyFramework",
Expand All @@ -14,4 +15,5 @@
"Aegis",
"BeaverTails",
"MITRE",
"HarmActEval",
]
3 changes: 2 additions & 1 deletion deepteam/frameworks/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
from .mitre.mitre import MITRE
from .risk_category import RiskCategory
from .owasp_top_10_agentic.owasp_top_10_agentic import OWASP_ASI_2026
from .harmacteval.harmacteval import HarmActEval
from .owasp.risk_categories import OWASP_CATEGORIES
from .nist.risk_categories import NIST_CATEGORIES
from .mitre.risk_categories import MITRE_CATEGORIES
Expand All @@ -17,7 +18,7 @@
f.name: f for f in [OWASPTop10, NIST, MITRE, OWASP_ASI_2026]
}

DATASET_FRAMEWORKS_MAP = {f.name: f for f in [Aegis, BeaverTails]}
DATASET_FRAMEWORKS_MAP = {f.name: f for f in [Aegis, BeaverTails, HarmActEval]}


class RiskCategoryInfo(BaseModel):
Expand Down
Loading