@vib795/agent-memory 0.5.1 → 0.5.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +27 -0
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -207,6 +207,33 @@ name on it. What this is not: it is not encryption, access control, or a DLP pro
207
207
  It is one command that refuses to hand over identifiers, and it says exactly what it
208
208
  checked.
209
209
 
210
+ ### Independently scanned
211
+
212
+ Public supply-chain scanners index every package published to npm, so this one is
213
+ reviewed by people who owe it nothing. That is worth more than a clean claim from its
214
+ author.
215
+
216
+ [LPM Firewall](https://firewall.lpm.dev/npm/@vib795/agent-memory) currently reports
217
+ **Passed — safe to install**, with no policy match and no flagged code. Its reading of
218
+ the artefact — signed, provenance attached, zero dependencies, no install hooks — is a
219
+ third-party check on what this README says about itself. Four low-signal patterns
220
+ remain, and they are descriptive rather than policy: environment variables, scripts
221
+ present, filesystem, high-entropy strings. That is what a CLI which reads
222
+ `AGENT_MEMORY_HOME` and writes files in your home directory looks like from outside.
223
+
224
+ **It did not start there.** Version 0.3.1 was flagged **Critical — AI Agent Control
225
+ Hijack**, because `postinstall` wrote skill files into `~/.claude`, `~/.codex` and your
226
+ editor's prompt folder. The finding was correct. An install script that grants an AI
227
+ agent new instructions without the user asking is indistinguishable from an attack
228
+ that does exactly that, and good intent is not observable to a scanner. The hook was
229
+ removed in 0.4.0 rather than argued with, which is why `agent-memory setup` is a
230
+ command you type.
231
+
232
+ The 0.3.1 report is still public and still says Critical. Old version pages do not
233
+ come down, and they should not: a supply-chain record that could be edited after the
234
+ fact would be worth nothing. What a project can offer is the next version and the
235
+ reason for it.
236
+
210
237
  ## Engagements
211
238
 
212
239
  If you work for more than one client on one machine, knowledge from one of them is
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@vib795/agent-memory",
3
- "version": "0.5.1",
3
+ "version": "0.5.2",
4
4
  "description": "Durable cross-repo knowledge graph for GitHub Copilot and Claude Code. Markdown source of truth, disposable SQLite index, zero runtime dependencies.",
5
5
  "keywords": [
6
6
  "github-copilot",