risk-assessment-9f2740 96/100

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

30.8 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 1 flagged

Securityscore 88 · 1 finding

MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · README.md

MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.

Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted

excerptREADME.md· markdown

103Rosetta instructions require the agent to: critically review every user request before execu

… (105 chars elided on L103)

104

1053. **Human-in-the-loop at decision points, not after the damage.** AI coding agents fully an

… (108 chars elided on L105)

106

107Rosetta workflows define approval gates at critical decision points: after specs, after plan

… (105 chars elided on L107)

Occurrences

1 occurrence · at L105

How to fix

Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.

Delete blanket "don't ask / no need to confirm" directives from the skill.
If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.

Framework references

OWASPLLM01 ATLASAML.T0051

Trace & refs

ruleSS-SKILL-INJECT-DONT-ASK-01sha25614b7852251bf4666…rubric 365aacaView on GitHub

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

plugins/core-claude/skills/risk-assessment/SKILL.md · 1 file

plugins/core-claude/skills/risk-assessment/SKILL.md1.1 KB · Markdown

name: risk-assessment

description: "MUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems, and when assessing environment risk level. SHOULD be invoked manually before any new environment interaction."

license: Apache-2.0

disable-model-invocation: false

user-invocable: false

argument-hint: environment-name

baseSchema: docs/schemas/skill.md

<risk_assessment>

Assess access to dangerous MCPs (database, cloud, S3, similar).
Assign risk level: low, medium, high, critical.
Read-only or local = low.
Shared dev/stage/qa = medium.
+1 level for write access.
+1 level for access to higher environments including production.
Output AI Risk Assessment: {LEVEL}.

Escalation:

MEDIUM: warn user, explain failure modes.
HIGH: require user to understand data loss risk.
CRITICAL: block execution, require external risk reduction. OVERRIDE NOT ALLOWED.

</process>

Defaulting to "low" without checking accessible MCPs.
Not re-assessing when new environments join mid-session.

</pitfalls>

</risk_assessment>

risk-assessment-9f2740— agent skill

Is risk-assessment-9f2740 safe to install?

Audit the pieces. Scan the whole. Decide.