Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PlamenTSV/plamen --skill cid-capability-safetygit clone --depth 1 https://github.com/PlamenTSV/plamenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/plamentsv/plamen/cid-capability-safety)<a href="https://agentmods.dev/skills/plamentsv/plamen/cid-capability-safety"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/cid-capability-safety/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/plamentsv/plamen/cid-capability-safety"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/cid-capability-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01537 |
| Opus 5 | $0.00014 | $0.00768 |
| Sonnet 5 | $0.00006 | $0.00307 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
cid-capability-safety scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CID_CAPABILITY_SAFETY Skill (DAML)
Trigger Pattern: Always required for DAML audits Inject Into: Breadth agents, depth-external, depth-edge-case Finding prefix:
[DML-CC-N]Rules referenced: R4, R8, R12
A ContractId t is a DAML-distinctive capability: holding one lets a party fetch/exercise the referenced contract. When a choice accepts a ContractId as an argument, that CID is attacker-chosen unless the body re-binds it to the operation. The four high-yield bug shapes: (1) caller-supplied CID not bound to the operation (caller passes a lookalike), (2) a config/whitelist CID that is missing → the choice fails open, (3) a hardcoded/stale config CID that has been archived → the choice bricks, (4) wrong-CID / type confusion via unchecked fromInterfaceContractId coercion.
1. Caller-Supplied CID Inventory
For every choice that takes a ContractId argument, determine whether the body binds it to the operation:
| Template.Choice | CID Arg | Fetched/Exercised? | Bound To Operation? | Binding Check | Finding? |
|---|---|---|---|---|---|
{T.C} |
cid : ContractId T2 |
YES/NO | YES/NO | assertMsg ... (fetched.owner == this.owner) / NONE |
[DML-CC-N] if unbound |
Critical patterns to flag:
- A choice that
fetch cidand then acts on the fetched contract's fields without asserting the fetched contract relates tothis(e.g., same owner, same asset, expected template) — caller passes any CID they can see ([ELEVATE:CID_BINDING]). - A choice that exercises a caller-supplied CID to move value, with no check that the CID is the intended counterparty contract.
DAML note: fetch cid succeeds for ANY contract the exercising party is a stakeholder of (or that is divulged). There is no implicit "this is the right contract" guarantee — the body MUST assert the relationship.
2. Config / Whitelist CID Fail-Open
A choice that looks up a config or whitelist contract by CID and proceeds when it is absent fails open.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 83 lines · 28 tokens per session scan A f65a91e300d4
cid-capability-safety is a skill published in the GitHub repository PlamenTSV/plamen (294 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,537 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
framework-compliance-triage
Make a cloud account compliant with a security or industry framework using Prowler Cloud.
prowler-ui
Prowler UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-16, tailwind-4. Trigger: When working inside ui/ on Prowler-specific conventions (shadcn, folder placement, actions/adapters, shared types/hooks/lib).
prowler-pr
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml…
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
tailwind-4
Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind (className, variants, cn()), especially when dynamic styling or CSS variables are involved (no var() in className).
prowler-docs
Prowler documentation style guide and writing standards. Trigger: When writing documentation for Prowler features, tutorials, or guides.