v0.1.0

Engrm Delivery Review

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:36 AM.

Analysis

This instruction-only skill coherently guides an agent to review delivery evidence with Engrm, with the main thing to notice being that it may save review conclusions to persistent memory.

GuidanceThis skill appears safe and narrowly scoped. Before using it, understand that it may save review outcomes and lessons into Engrm memory, so make sure those saved notes are accurate and do not include unnecessary sensitive information.

Findings (1)

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.

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

SKILL.md

Save:

- the real outcome
- the main gap or drift
- the lesson future sessions should know first

The skill explicitly directs the agent to save conclusions for future use, creating persistent context. This is aligned with the delivery-review purpose, but users should understand that saved memories can influence later sessions.

User impactThe agent may store a summary of what really happened in a session, including gaps or drift, and that stored context may shape future work.

RecommendationReview or correct saved Engrm entries when needed, and avoid storing sensitive details unless they are necessary for future project context.