truefoundry-applications
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides automated routines in
references/prerequisites.mdto install thetruefoundryCLI package from PyPI. This is a vendor-owned package essential for the skill's operations. - [COMMAND_EXECUTION]: The skill utilizes a Bash script (
scripts/tfy-api.sh) to perform authenticatedcurlrequests to the TrueFoundry API. The script includes basic security checks to prevent path traversal. - [DYNAMIC_EXECUTION]: The skill uses Python one-liners in
SKILL.mdto parse and format JSON data returned from API calls. These commands follow static templates for data processing. - [INDIRECT_PROMPT_INJECTION]: The skill processes deployment metadata and statuses from the TrueFoundry API, which constitutes a surface for indirect prompt injection.
- Ingestion points: Application names, deployment statuses, and logs are retrieved from the TrueFoundry API and ingested into the agent's context in
SKILL.md. - Boundary markers: None are present in the provided instructions or data processing scripts.
- Capability inventory: The skill can perform network operations via
tfy-api.shand execute shell commands to interact with the platform. - Sanitization: The skill does not explicitly sanitize or filter strings returned from the API before presenting them to the user or processing them further.
Audit Metadata