CC adaptlypost
Schedule, publish and review social posts through the AdaptlyPost API on Instagram, X (Twitter), Bluesky, TikTok, Threads, LinkedIn, Facebook, Pinterest and YouTube accounts connected to AdaptlyPost, and read their analytics. Use only when the user has an AdaptlyPost account and asks to draft, schedule or publish a post on those accounts, upload media for such a post, list the connected accounts, check a post's status, or ask about views, likes, comments, followers or top posts on them. Do not use for writing captions without posting, general social media advice, or accounts that are not connected to AdaptlyPost.
Schedule, publish and review social posts through the AdaptlyPost API on Instagram, X (Twitter), Bluesky, TikTok, Threads, LinkedIn, Facebook, Pinterest and…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Broad scope
meta-requests-env-secretSKILL.md:1Skill asks the runtime to inject credential env vars into its sandbox: ADAPTLYPOST_API_KEY — verify each one is needed for the stated purposerequired_environment_variables: ADAPTLYPOST_API_KEY
-
medium Exfiltration
net-credential-useSKILL.md:76Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $ADAPTLYPOST_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:204Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $ADAPTLYPOST_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:213Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $ADAPTLYPOST_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:268Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $ADAPTLYPOST_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:334Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $ADAPTLYPOST_API_KEY" \
-
low Secrets in code
secret-high-entropy-tokenreferences/api-reference.md:156High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"userId": "user…XDS",
quoted
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 620 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
body-longSKILL.md body ≈ 7113 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "required_environment_variables"
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 51 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Steps. 53 steps, 4 vague phrases
- 60Consistency. The Hermes dialect needs category and tags
- 70Execution cost. Instruction body is 7113 tokens
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 8 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (3 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 620: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.