MCP, MCP server
Widemem Ai
Goldfish memory?
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
SECRETS_PATH_CREDENTIAL AGENT_IGNORE_INSTRUCTIONS
Why this grade
- SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
.gitignore, line 13
credentials.json - AGENT_IGNORE_INSTRUCTIONS Medium
Text tells the agent to ignore earlier instructions.
docs/guide.md, line 352
- Direct instruction overrides (`ignore previous instructions`, `disregard the rules`, `forget what I said`)
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Concern
can delete files.
PERMISSION_DELETE_FILES
benchmark/val.py, line 304
shutil.rmtree(base)
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Pass
No network call found.
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
benchmark/mini_locomo.py, line 53
set -a; source .env.local; set +a # load OPENAI_API_KEY
benchmark/mini_locomo.py, line 491
if not os.environ.get("OPENAI_API_KEY"):
.gitignore, line 13
credentials.json
Show more
benchmark/mini_locomo.py, line 492
print("ERROR: OPENAI_API_KEY not set. `set -a; source .env.local; set +a` first.")
benchmark/run_ws1.py, line 37
set -a; source .env.local; set +a # load OPENAI_API_KEY
benchmark/run_ws1.py, line 650
if not os.environ.get("OPENAI_API_KEY"):
benchmark/val.py, line 24
set -a; source .env.local; set +a
benchmark/val.py, line 387
if not os.environ.get("OPENAI_API_KEY"):
scripts/e2e_test.py, line 17
api_key = os.environ.get("OPENAI_API_KEY")
widemem/server.py, line 76
has_key = bool(os.environ.get("WIDEMEM_API_KEY"))
widemem/server.py, line 111
expected = os.environ.get("WIDEMEM_API_KEY")
.gitignore, line 10
.env
benchmark/MINI_LOCOMO.md, line 67
set -a; source .env.local; set +a # load OPENAI_API_KEY
Agent instructions
Serious
instructions tell the agent to ignore earlier instructions.
AGENT_IGNORE_INSTRUCTIONS
docs/guide.md, line 352
- Direct instruction overrides (`ignore previous instructions`, `disregard the rules`, `forget what I said`)
Obfuscation
Pass
No encoded or minified payload found.
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit bf3328d92cb9. can delete files. reads a credential or environment file. instructions tell the agent to ignore earlier instructions.
Date and source
Date checked:
github.com
Commit graded: bf3328d92cb950f8ec79b9bd5dfafc7bb2238605
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.