basecamp
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates communication with the Basecamp API via a proxy, creating an attack surface where malicious content stored in Basecamp could influence the agent's behavior.
- Ingestion point: The agent ingests external data from Basecamp through the
https://unify.apideck.com/proxyendpoint as described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the retrieved data.
- Capability inventory: The agent is instructed to use network tools (such as
curl) to perform GET, POST, PATCH, PUT, and DELETE operations. - Sanitization: There are no instructions provided for sanitizing, escaping, or validating the content returned from the downstream Basecamp API.
- [NO_CODE]: This skill consists entirely of instructional markdown and configuration metadata. It does not include any scripts, executable code, or package dependency files.
Audit Metadata