DF agent-memory
Agent 记忆系统 — 五路融合检索 + 双时间线 + 因果链 + Spirit管家 + 记忆回声 + 弹性配置 + Circuit Breaker + GDPR合规 + 192项安全审计修复
As a process F 41/100 · Will not run — References files that are not bundled: API.md
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 9
-
high Exfiltration
exfil-webhook-urlRUNBOOK.md:188Webhook / callback URL commonly used for exfiltration (verify the destination)export AGENT_MEMORY_ALERT_WEBHOOK_URL=https://hooks.slack.com/services/xxx
Medium and low: 8
-
medium Exfiltration
net-redirectable-api-keyagent_memory/embedding_store.py:728Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyagent_memory/llm_client.py:49Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyagent_memory/media_processor.py:107Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Dangerous commands
cmd-install-from-urlRELEASE_CHECKLIST.md:17Installs a package from an untrusted URL / archive (quoted — discussed, not commanded)- [ ] Package installs: `pip install dist/agen…whl`
quoted -
low Secrets in code
secret-high-entropy-tokenagent_memory/api_v2.py:505High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"xK9m…3eG",
quoted -
low Secrets in code
secret-high-entropy-tokenagent_memory/api_v3.py:432High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"xK9m…3eG",
quoted -
low Secrets in code
secret-high-entropy-tokenagent_memory/media_processor.py:148High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)boundary = "----…0gW"
quoted -
low Dangerous commands
cmd-background-processagent_memory/model_server.py:556Starts a background / autostarted processos.setsid()
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: API.md - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "repository" - note
frontmatter-keyunknown frontmatter key "install" - note
frontmatter-keyunknown frontmatter key "credentials" - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 41/100
- 0Tools and files. 1 referenced file(s) missing: API.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (agent-memory) differs from the folder (super-memory)
- 100Steps. 52 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 3252 tokens
- 100Running it twice. No mutating operations
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 97: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -220 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Structure: 24 headings
- +3Step-by-step instructions: 52 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.