Instruction Anchor Guard
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is purpose-aligned, but it intentionally stores persistent instruction anchors that can influence future planning.
This skill appears safe for its stated purpose. Before installing, be comfortable with it keeping a local ledger of important instructions that may affect future turns, and review or delete anchors that become outdated.
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.
Important instructions may persist across long sessions or compaction and shape later actions, including if an anchor becomes outdated or was captured too broadly.
The skill intentionally persists user instructions and reuses them in future planning, which is purpose-aligned but means stale or mistaken anchors can keep influencing behavior.
Store anchors in first available path: `memory/anchors.md` ... `.anchors.md`; ... Load active anchors ... Inject `ANCHOR_SET` into planning phase before tool execution
Use task or session scope when possible, avoid storing sensitive personal data, and periodically review `/anchors list` and pause or delete anchors that no longer apply.
It is harder to independently verify the publisher history or exact packaged version before installing.
The registry metadata lacks a source/homepage and does not align with the SKILL.md frontmatter version `1.1.0`; this is a provenance/versioning note, not evidence of malicious behavior.
Source: unknown; Homepage: none; Version: 1.0.0
Confirm the skill comes from a trusted publisher and that the installed version is the one you intended to use.