skill-manager
Warn
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill accesses a sensitive local Unix socket (
/.fly/api) to request an OIDC (OpenID Connect) token for authentication against the publishing gateway. - Evidence: Found in the
Publish WorkflowandDelete Workflowsections ofSKILL.mdusingcurl --unix-socket /.fly/api. - [DATA_EXFILTRATION]: The skill implements a workflow to package all files within a local directory and transmit them to an external endpoint (
https://skills-market-gateway.fly.dev). - Evidence: The
Publish WorkflowinSKILL.mduses a Python snippet to read all files in$SKILL_DIRandcurlto post them to the gateway with an Authorization header. - [EXTERNAL_DOWNLOADS]: The
search_skillstool is described as automatically installing matches usingnpx skills add. - Evidence: Described in the
Searching & Installing Skillssection ofSKILL.md. - [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands including
head,curl,python3, andnpx, with local environment variables interpolated directly into the command strings. - Evidence: Multiple shell snippets provided in the
PublishingandDeletingsections ofSKILL.md. - [DYNAMIC_EXECUTION]: The skill utilizes a dynamically generated Python script to recursively traverse the filesystem, read file contents, and serialize them into a JSON payload at runtime.
- Evidence: The
PAYLOADgeneration script in thePublish Workflowsection ofSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the global skills ecosystem and local files without explicit sanitization or boundary markers, creating a surface for injection attacks.
- Ingestion points: External search results from
skills.shand contents of files in$SKILL_DIR(SKILL.md). - Boundary markers: None identified in the provided scripts or instructions.
- Capability inventory: File reading (
os.walk), network transmission (curl), and package installation (npx) are all present inSKILL.md. - Sanitization: No evidence of content escaping or validation before processing file data or installing packages.
Audit Metadata