v1.0.18

Find Book

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 7:57 AM.

Analysis

Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.

GuidanceThis looks reasonable for local book lookup. Before installing, be aware that the rating/data source is not clearly Goodreads-backed, provenance is limited, and any suggested SOUL/MEMORY/SKILL additions should be reviewed before saving. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.

Findings (3)

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.

Human-Agent Trust Exploitation

SeverityLowConfidenceHighStatusNote

metadata

Description: Instantly find nonfiction books with Goodreads ratings, summaries, key concepts...

The included SKILL.md, README.md, package metadata, and code describe a Heardly/local dataset rather than a demonstrated Goodreads source. This may affect user trust in the ratings, but it does not show unsafe execution.

User impactUsers may believe ratings come from Goodreads when the artifacts support only a local Heardly/bookscore dataset.

RecommendationTreat the ratings as local/Heardly-provided unless the maintainer documents Goodreads provenance.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceHighStatusNote

metadata

Source: unknown; Homepage: none

The registry does not provide a source repository or homepage for independent provenance checks. Because no remote install scripts or external dependencies are shown, this remains a low-level supply-chain notice.

User impactYou have less information for verifying who maintains the package or where the bundled data came from.

RecommendationInstall only if you trust the registry entry and maintainer; verify provenance if the dataset quality matters.

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

index.js

Generate markdown snippets for agent files ... SOUL: `## Books That Shaped Me` ... MEMORY: `## Learned Patterns` ... SKILL: `## Reference Books`

The skill creates text intended for persistent agent knowledge files, which could influence future agent behavior if a user copies it, although the code does not write those files itself.

User impactIf you save the suggested snippets to agent memory or identity files, book-summary content can become part of future agent context.

RecommendationReview and edit suggested additions before saving them to persistent agent files; do not add snippets automatically.