DD beam
Beam: verified bucket transfers, fan-out and agent Rooms. Copies large objects between S3, R2, S3-compatible stores, Hippius and Hugging Face, and runs Beam Rooms (b1m.ai) for messages, streams and files between agents.
Beam: verified bucket transfers, fan-out and agent Rooms.
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 5
-
high Broad scope
meta-requests-env-secretSKILL.md:1Skill asks the runtime to inject credential env vars into its sandbox: BEAM_API_KEY, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN, R2_ACCESS_KEY_ID, R2_SECRET_ACCESS_KEY, S3_ACCESS_KEY_ID, S3_SECRET_ACCESS_KEY, HIPPIUS_API_TOKEN, HF_TOKEN (high-value: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN, HF_TOKEN) — verify each one is needed for the stated purposerequired_environment_variables: BEAM_API_KEY, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN, R2_A…_ID, R2_S…KEY, S3_A…_ID, S3_S…KEY, HIPPIUS_API_T
Medium and low: 4
-
low Exfiltration
net-credential-usereferences/transfers.md:144Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)printf 'X-Api-Key: %s\n' "$BEAM_API_KEY" | curl -fsS -H @- "https://beam….ai/transfers/$TRANSFER_ID"
quoted -
low Exfiltration
net-credential-usereferences/transfers.md:145Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)printf 'X-Api-Key: %s\n' "$BEAM_API_KEY" | curl -fsS -H @- "https://beam….ai/transfers?status=…&limit=10"
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/beam_transfer.py:45High-entropy token-like string (may be an id, hash or a credential)S3Co…ion,
-
low Secrets in code
secret-high-entropy-tokenscripts/beam_transfer.py:244High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)model = S3Co…rce if source else S3Co…ion
detector
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 219 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "required_environment_variables"
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 39 steps
- 100Execution cost. Instruction body is 2452 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (5 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 219: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.