v1.2.0

Portable Tools

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 4:52 AM.

Analysis

Review before installing: the skill is mostly a local portability checklist, but its instructions encourage showing real OAuth/access-token values, which could expose credentials.

GuidanceUse the local checklist only on intended project folders. More importantly, do not follow the examples by pasting or printing real OAuth/access tokens; redact them, hash them, or show non-secret proof such as expiry changes before sharing output.

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

pre-publish-checklist.sh

TARGET="${1:-.}" ... HARDCODED_PATHS=$(grep -r "/Users/" "$TARGET" --include="*.sh" --include="*.bash" --include="*.py" ...)

The helper recursively scans a user-selected directory and prints some matching lines; this is purpose-aligned for a pre-publish checklist but should be pointed only at code the user intends to inspect.

User impactIf run on an overly broad directory, it may inspect more local files than intended and display matching local path lines.

RecommendationRun the checklist only against the specific project directory you want reviewed, not your home directory or unrelated private folders.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityHighConfidenceHighStatusConcern

SKILL.md

security find-generic-password -s "Service" -w ... Require: Concrete BEFORE state (exact values) ... BEFORE: - Access Token: POp5z1fi...eSN9VAAA ... Action: Always show data transformation with real values

The skill uses keychain/OAuth-token examples and explicitly tells the user or agent to show real exact values as proof, which can expose credentials in conversations, logs, or published documentation.

User impactReal access or refresh tokens could be pasted into chat history or files, allowing anyone with access to those records to misuse the account until the token expires or is revoked.

RecommendationDo not print full tokens. Use redacted prefixes, hashes, token IDs, expiry timestamps, or boolean validation results, and require explicit user approval before reading keychains or credential stores.