Security audit
Security checks across malware telemetry and agentic risk
This skill is a disclosed eval-building workflow that writes and runs skill evaluation files, with no evidence of hidden, deceptive, or unrelated behavior.
Install this if you want an agent to help create and run evals for skills. Be aware it can write .eval.yaml files beside a skill and run Caliper/agent CLI commands, so review proposed eval content before confirming writes or runs.
the SKILL.md, gives some understanding of the skill, and asks the user for
input before generating anything — then STOPS to wait. The number of
questions does not matter. Fail if the agent skips the interview: it
invents the user's answers, generates the eval tasks itself without
asking, or writes any .eval.yaml file in this turn.
assert: |
import glob# a deterministic guard that it did NOT fabricate answers and write a spec.
- name: Interviews before generating — asks, then stops (does not run ahead)
setup: |
rm -rf /tmp/grill-fresh
mkdir -p /tmp/grill-fresh
cat > /tmp/grill-fresh/SKILL.md << 'EOF'
---# existing spec was left untouched in this first turn.
- name: Detects an existing eval and asks before touching it
setup: |
rm -rf /tmp/grill-existing
mkdir -p /tmp/grill-existing
cat > /tmp/grill-existing/SKILL.md << 'EOF'
---# workflow and the one task with a full artifact assert.
- name: Serializes a valid 3-task spec when the structure is given
setup: |
rm -rf /tmp/grill-serialize
mkdir -p /tmp/grill-serialize
cat > /tmp/grill-serialize/SKILL.md << 'EOF'
---# a deterministic guard that it did NOT fabricate answers and write a spec.
- name: Interviews before generating — asks, then stops (does not run ahead)
setup: |
rm -rf /tmp/grill-fresh
mkdir -p /tmp/grill-fresh
cat > /tmp/grill-fresh/SKILL.md << 'EOF'
---Read the merged PRs since the last tag and write a grouped changelog
entry (Features / Fixes / Chore) to CHANGELOG.md.
EOF
cleanup: rm -rf /tmp/grill-fresh
prompt: >
I want to create a caliper eval for my skill at
/tmp/grill-fresh/SKILL.md. I'm here and will answer whatever you need —# existing spec was left untouched in this first turn.
- name: Detects an existing eval and asks before touching it
setup: |
rm -rf /tmp/grill-existing
mkdir -p /tmp/grill-existing
cat > /tmp/grill-existing/SKILL.md << 'EOF'
---prompt: Summarize /tmp/notes.txt
expect: The agent produces a summary of the file contents.
EOF
cleanup: rm -rf /tmp/grill-existing
prompt: >
I want to improve the eval for my skill at
/tmp/grill-existing/SKILL.md using grill-skill. I'm here to answer your# workflow and the one task with a full artifact assert.
- name: Serializes a valid 3-task spec when the structure is given
setup: |
rm -rf /tmp/grill-serialize
mkdir -p /tmp/grill-serialize
cat > /tmp/grill-serialize/SKILL.md << 'EOF'
---Write the text "hello world" to /tmp/hello.txt when the user asks.
EOF
cleanup: rm -rf /tmp/grill-serialize
prompt: >
Write the file directly now — do NOT ask me any clarifying questions
first; I have given you everything you need. Use the grill-skill to write64/64 vendors flagged this skill as clean.
No suspicious patterns detected.