context-receipts
Audit Context Boundaries with Privacy-Safe Receipts
Context-saving workflows often lack evidence about what crossed an agent boundary. This skill defines privacy-safe receipts for routing, loading, suppression, and audit gaps.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "context-receipts" from https://skillstore.io/skills/caioribeiroclw-pixel-context-receipts.md and its manifest at https://skillstore.io/api/skills/caioribeiroclw-pixel-context-receipts/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "context-receipts". A Tool Search session starts with 84 deferred tools and hydrates one definition.
Expected outcome:
- Startup loaded an index for 84 tools and no full schemas.
- One definition was hydrated after search; 83 tools remained suppressed.
- Arguments and results were redacted. Tool relevance remains unproven.
Using "context-receipts". A compaction request fails before context replacement.
Expected outcome:
- Summary generation failed and no candidate summary was available.
- The original context and deferred-tool registry were preserved.
- No stale reminders replayed. Semantic quality was not evaluated.
Using "context-receipts". A retrieval workflow returns five chunks but loads only three into agent context.
Expected outcome:
- Three retrieved chunks were loaded; two stale or duplicate chunks were suppressed.
- Only hashes, rank buckets, and counts were recorded.
- The receipt proves delivery, not answer correctness.
Security Audit
Medium RiskAll 49 static findings are false positives: README paths are fixed references, SKILL.md backticks are Markdown, and reconnaissance matches are audit prose. However, README.md instructs readers to execute four Node scripts outside the scanned skill package. Those scripts require separate review before use.
Confirmed security concerns (1)
Risk Factors
📁 Filesystem access (8)
⚙️ External commands (32)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/caioribeiroclw-pixel-context-receipts/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/caioribeiroclw-pixel-context-receipts?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/caioribeiroclw-pixel-context-receipts?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/caioribeiroclw-pixel-context-receipts/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/caioribeiroclw-pixel-context-receipts.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
caioribeiroclw-pixel. (2026). context-receipts security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/caioribeiroclw-pixel-context-receipts/audits/5BibTeX citation
@techreport{caioribeiroclw-pixel-caioribeiroclw-pixel-context-receipts-2026,
author = {caioribeiroclw-pixel},
title = {context-receipts security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/caioribeiroclw-pixel-context-receipts/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "context-receipts security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "caioribeiroclw-pixel"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/caioribeiroclw-pixel-context-receipts/audits/5"
identifiers:
- type: other
value: "skillstore:caioribeiroclw-pixel-context-receipts:audit:5"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Audit MCP Tool Loading
Validate which MCP tools were discovered, hydrated, activated, withheld, or called without exposing schemas, arguments, results, or prompts.
Verify Retrieved Context Attention
Confirm that required context was delivered, acknowledged before planning, and cited before edits while preserving content privacy.
Review Context Budget Changes
Trace pruning, compaction, rollback, usage attribution, and delegation to determine whether claimed context savings have supporting evidence.
Try These Prompts
Create a privacy-safe receipt for [workflow]. Include stable IDs, counts, token buckets, redaction flags, and one explicit audit gap.
Review [receipt] for raw prompts, schemas, arguments, results, secrets, customer names, and transcript text. Report every privacy violation.
Compare [before state] and [after state]. Produce a tool-surface receipt covering discovery, activation, blocking, redaction, and unresolved evidence gaps.
Design a receipt chain for [workflow]. Trace delegation, tool exposure, retrieval, compaction rollback, usage attribution, and raw-content boundary decisions.
Best Practices
- Use stable or hashed identifiers instead of raw prompts, paths, schemas, customer data, or tool results.
- Record before-and-after buckets, suppression reasons, redaction flags, and rollback outcomes.
- State an audit gap that distinguishes proven boundary behavior from unverified semantic quality.
Avoid
- Do not copy raw prompts, schemas, arguments, results, transcripts, secrets, or customer names into receipts.
- Do not treat successful tool execution as proof that the selected tool was relevant.
- Do not claim context savings when the receipt lacks before-and-after evidence.
Frequently Asked Questions
What is a context receipt?
Does the skill store raw prompts?
Which workflows are covered?
Does a receipt prove output correctness?
Can receipts measure context savings?
Is receipt generation automatic?
Developer Details
Author
caioribeiroclw-pixelLicense
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
a39a91716eadede5f4cdefd78178fed4e837a128
Maintenance freshness
7/24/2026
Usage
5 downloads · 0 views