call-adcp-agent
call-adcp-agent is an API access & connector plumbing skill for AI agents, published by adcontextprotocol in the adcp repository on GitHub. Skillspace rates call-adcp-agent D (65/100) and the safety scan flagged it for review; the rating is based on static analysis only.
Flagged for review. Read the source before running it.
Wire-level invariants for any AdCP buyer call — idempotency_key replay semantics, account `oneOf` variants, async `status:'submitted'`+`task_id` polling, error recovery from `adcp_error.issues[]`. Load before any per-protocol task skill (adcp-media-buy, adcp-creative, adcp-signals, adcp-governance, adcp-si, adcp-brand) when calling an AdCP agent as a buyer.
- Grade
- D
- Quality
- 65 / 100
- Safety
- Needs review
- GitHub stars
- 235
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 95 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Medium-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 2 other repositories, in 0 collections
What the scanner flagged
- suspicious outbound endpoint
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.