fittings-rxterms-prescribable
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a helper script (
call.mjs) from the vendor's official domainfittings.shto facilitate API requests. - [COMMAND_EXECUTION]: The instructions direct the agent to execute the downloaded
call.mjsscript usingnodeto interact with the drug lookup service. - [CREDENTIALS_UNSAFE]: The skill's payment mechanism requires a
FITTINGS_PRIVATE_KEYenvironment variable. The documentation includes security guidance advising the use of a throwaway wallet because the key may be stored in plaintext. - [INDIRECT_PROMPT_INJECTION]: The skill ingests drug information from an external API, creating a surface for potential injection if the source data is compromised.
- Ingestion points: Data returned from
https://fittings.sh/v1/rxterms/prescribable(file: SKILL.md). - Boundary markers: None present; the skill lacks specific delimiters to separate external data from system instructions.
- Capability inventory: Uses
curlfor downloads andnodefor script execution (file: SKILL.md). - Sanitization: No explicit sanitization or validation logic is described for the incoming API data.
Audit Metadata