outdated
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
pnpm outdatedandpnpm viewto collect information about project dependencies. These are standard developer tools used for their intended purpose of dependency management and auditing.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external and local sources, which represents a potential attack surface for indirect prompt injection, although the risk is minimal given the skill's limited output scope.\n - Ingestion points: Package metadata from the npm registry (via
pnpm view) and existing entries intmp/UPGRADES.md(SKILL.md).\n - Boundary markers: None present; the skill treats data from the registry and the local file as trusted content for the report.\n
- Capability inventory: The skill is capable of querying external package registries and writing to the local filesystem.\n
- Sanitization: No specific sanitization or validation of the ingested package metadata is performed before it is formatted into the markdown report.
Audit Metadata