v1.0.1

Policy Lawyer

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 5:17 AM.

Analysis

This skill coherently reads a small policy reference document or a user-specified policy file and has no evidence of hidden execution, credential use, network access, or destructive behavior.

GuidanceThis appears safe for normal policy lookup. Before installing, be aware that it can read whichever local policy file path it is given, and treat policy output from other workspaces as untrusted until you verify it.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityLowConfidenceHighStatusNote

scripts/policy_lawyer.py

parser.add_argument("--policy-file", type=Path, default=Path(__file__).resolve().parent.parent / "references" / "policies.md", help="Path to the policy reference document.")

The CLI can read a local file path supplied by the user. This is expected for comparing policy documents, but it means users should avoid pointing it at unrelated private files.

User impactIf invoked with the wrong file path, the skill may print contents from a local file that was not meant to be used as a policy reference.

RecommendationUse --policy-file only with intended, trusted policy documents and review output before quoting it as authoritative.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceHighStatusNote

references/policies.md

Log every sensitive action in `memory/YYYY-MM-DD.md` so auditors can reconstruct decisions.

The policy content that this skill may quote recommends persistent logging of sensitive actions. The skill does not write those logs itself, but users should be careful about what sensitive details get persisted if they follow the policy.

User impactFollowing the quoted policy could create persistent records about sensitive actions, which may be useful for audits but should not include secrets or excessive private details.

RecommendationWhen following this policy, log only necessary audit information and avoid storing secrets, tokens, or private file contents in memory logs.